Visual communication often needs stylistically consistent icons that span concrete and abstract meanings, for use in diverse contexts. We present Iconix, a human-AI co-creative system that organizes icon generation along two axes: semantic richness (what is depicted) and visual complexity (how much detail). Given a user-specified concept, Iconix constructs a semantic scaffold of related analytical perspectives and employs chained, image-conditioned generation to produce a coherent style of exemplars. Each exemplar is then automatically distilled into a progressive sequence, from detailed and elaborate to abstract and simple. The resulting two-dimensional grid exposes a navigable space, helping designers reason jointly about figurative content and visual abstraction. A within-subjects study (N = 32) found that compared to a baseline workflow, participants produced icon grids more creatively, reported lower workload, and explored a coherent range of design variations. We discuss implications for human-machine co-creative approaches that couple semantic scaffolding with progressive simplification to support visual abstraction.

Traditional statistical graphics are precise but often lack the visual appeal, memorability, and engagement of pictorial charts. We present a generative framework for the automated synthesis of pictorial charts that bridges the gap between semantic expression and structural faithfulness. Rather than treating charts merely as images to be stylized, we frame the problem as a dual-conditioned generation task guided by two parallel external control signals: a text prompt capturing the semantic context of the editing intent, and a context image providing the abstract statistical chart's global structure. To reinforce these controls within a Multi-Modal Diffusion Transformer, we introduce two complementary feature-level mechanisms: structural alignment to anchor spatial layouts to the input chart, and semantic alignment to transfer expressive textures from reference images. Generalizing across major visual channels (i.e., length, area, angle, and position) and diverse semantic domains, our method produces pictorial charts that are both artistically compelling and structurally consistent. Extensive quantitative evaluations and perceptual user studies demonstrate that our framework outperforms traditional controllable generation and image editing baselines, providing a foundation for high-fidelity, data-driven generative modeling in expressive visual storytelling. Project page: https://ssalign.github.io/.

Affective Image Manipulation (AIM) seeks to modify user-provided images to evoke specific emotions. This task is inherently complex due to its twofold objective: evoking the intended emotion while preserving image composition. Existing AIM methods primarily adjust color and style, often failing to elicit precise, profound emotional shifts. Drawing on psychological insights, we introduce EmoEdit, which extends AIM by incorporating content modifications to enhance emotional impact. Specifically, we construct EmoEditSet, a large-scale AIM dataset of 40,120 paired data through emotion attribution and data construction. To make generative models emotion-aware, we design an Emotion Adapter and train it using EmoEditSet. We further propose an instruction loss to capture semantic variations in each data pair. Our method is evaluated both qualitatively and quantitatively, demonstrating superior performance over state-of-the-art techniques. Additionally, we showcase the portability of our Emotion Adapter to other diffusion-based models, enhancing their emotion knowledge with diverse semantics. Code is available at: https://github.com/JingyuanYY/EmoEdit.

Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and sampling. However, they exhibit limited generation diversity. In this work, we leverage this limitation to perform consistent image edits via selective injection of attention features. The main challenge is that, unlike the UNet-based models, DiT lacks a coarse-to-fine synthesis structure, making it unclear in which layers to perform the injection. Therefore, we propose an automatic method to identify "vital layers" within DiT, crucial for image formation, and demonstrate how these layers facilitate a range of controlled stable edits, from non-rigid modifications to object addition, using the same mechanism. Next, to enable real-image editing, we introduce an improved image inversion method for flow models. Finally, we evaluate our approach through qualitative and quantitative comparisons, along with a user study, and demonstrate its effectiveness across multiple applications.

As 3D content creation continues to grow, transferring semantic textures between 3D meshes remains a significant challenge in computer graphics. While recent methods leverage text-to-image diffusion models for texturing, they often struggle to preserve the appearance of the source texture during texture transfer. We present TriTex, a novel approach that learns a volumetric texture field from a single textured mesh by mapping semantic features to surface colors. Using an efficient triplane-based architecture, our method enables semantic-aware texture transfer to a novel target mesh. Despite training on just one example, it generalizes effectively to diverse shapes within the same category. Extensive evaluation on our newly created benchmark dataset shows that TriTex achieves superior texture transfer quality and fast inference times compared to existing methods. Our approach advances single-example texture transfer, providing a practical solution for maintaining visual coherence across related 3D models in applications like game development and simulation. Project page: https://danacohen95.github.io/TriTex/.

We introduce Omni-ID, a novel facial representation designed specifically for generative tasks. Omni-ID encodes holistic information about an individual’s appearance across diverse expressions and poses within a fixed-size representation. It consolidates information from a varied number of unstructured input images into a structured representation, where each entry represents certain global or local identity features. Our approach uses a few-to-many identity reconstruction training paradigm, where a limited set of input images is used to reconstruct multiple target images of the same individual in various poses and expressions. A multi-decoder framework is introduced to leverage the complementary strengths of diverse decoders during training. Unlike conventional representations, such as ArcFace and CLIP, which are typically learned through discriminative or contrastive objectives, Omni-ID is optimized with a generative objective, resulting in a more comprehensive and nuanced identity capture for generative tasks. Trained on our MFHQ dataset – a multi-view facial image collection, Omni-ID demonstrates substantial improvements over conventional representations across various generative tasks.

This work presents a progressive image vectorization technique that reconstructs the raster image as layer-wise vectors from semantic-aligned macro structures to finer details. Our approach introduces a new image simplification method leveraging the feature-average effect in the Score Distillation Sampling mechanism, achieving effective visual abstraction from the detailed to coarse. Guided by the sequence of progressive simplified images, we propose a two-stage vectorization process of structural buildup and visual refinement, constructing the vectors in an organized and manageable manner. The resulting vectors are layered and well-aligned with the target image’s explicit and implicit semantic structures. Our method demonstrates high performance across a wide range of images. Comparative analysis with existing vectorization methods highlights our technique’s superiority in creating vectors with high visual fidelity, and more importantly, achieving higher semantic alignment and more compact layered representation.

Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and construct compelling narratives. Crafting animations that are semantically aware poses significant challenges, demanding expertise in graphic design and animation. We present an automated text animation scheme, termed "Dynamic Typography", which combines two challenging tasks. It deforms letters to convey semantic meaning and infuses them with vibrant movements based on user prompts. Our technique harnesses vector graphics representations and an end-to-end optimization-based framework. This framework employs neural displacement fields to convert letters into base shapes and applies per-frame motion, encouraging coherence with the intended textual concept. Shape preservation techniques and perceptual loss regularization are employed to maintain legibility and structural integrity throughout the animation process. We demonstrate the generalizability of our approach across various text-to-video models and highlight the superiority of our end-to-end methodology over baseline methods, which might comprise separate tasks. Through quantitative and qualitative evaluations, we demonstrate the effectiveness of our framework in generating coherent text animations that faithfully interpret user prompts while maintaining readability. Our code is available at: https://animate-your-word.github.io/demo/.

Vector graphics are essential in design, providing artists with a versatile medium for creating resolution-independent and highly editable visual content. Recent advancements in vision-language and diffusion models have fueled interest in text-to-vector graphics generation. However, existing approaches often suffer from over-parameterized outputs or treat the layered structure - a core feature of vector graphics - as a secondary goal, diminishing their practical use. Recognizing the importance of layered SVG representations, we propose NeuralSVG, an implicit neural representation for generating vector graphics from text prompts. Inspired by Neural Radiance Fields (NeRFs), NeuralSVG encodes the entire scene into the weights of a small MLP network, optimized using Score Distillation Sampling (SDS). To encourage a layered structure in the generated SVG, we introduce a dropout-based regularization technique that strengthens the standalone meaning of each shape. We additionally demonstrate that utilizing a neural representation provides an added benefit of inference-time control, enabling users to dynamically adapt the generated SVG based on user-provided inputs, all with a single learned representation. Through extensive qualitative and quantitative evaluations, we demonstrate that NeuralSVG outperforms existing methods in generating structured and flexible SVG.

Recent advances in text-to-video generation have enabled high-quality synthesis from text and image prompts. While the personalization of dynamic concepts, which capture subject-specific appearance and motion from a single video, is now feasible, most existing methods require per-instance fine-tuning, limiting scalability. We introduce a fully zero-shot framework for dynamic concept personalization in text-to-video models. Our method leverages structured 2×2 video grids that spatially organize input and output pairs, enabling the training of lightweight Grid-LoRA adapters for editing and composition within these grids. At inference, a dedicated Grid Fill module completes partially observed layouts, producing temporally coherent and identity preserving outputs. Once trained, the entire system operates in a single forward pass, generalizing to previously unseen dynamic concepts without any test-time optimization. Extensive experiments demonstrate high-quality and consistent results across a wide range of subjects beyond trained concepts and editing scenarios.

We pose a new problem, In-2-4D, for generative 4D (i.e., 3D + motion) inbetweening to interpolate two single-view images. In contrast to video/4D generation from only text or a single image, our interpolative task can leverage more precise motion control to better constrain the generation. Given two monocular RGB images representing the start and end states of an object in motion, our goal is to generate and reconstruct the motion in 4D, without making assumptions on the object category, motion type, length, or complexity. To handle such arbitrary and diverse motions, we utilize a foundational video interpolation model for motion prediction. However, large frame-to-frame motion gaps can lead to ambiguous interpretations. To this end, we employ a hierarchical approach to identify keyframes that are visually close to the input states while exhibiting significant motions, then generate smooth fragments between them. For each fragment, we construct a 3D representation of the keyframe using Gaussian Splatting (3DGS). The temporal frames within the fragment guide the motion, enabling their transformation into dynamic 3DGS through a deformation field. To improve temporal consistency and refine the 3D motion, we expand the self-attention of multi-view diffusion across timesteps and apply rigid transformation regularization. Finally, we merge the independently generated 3D motion segments by interpolating boundary deformation fields and optimizing them to align with the guiding video, ensuring smooth and flicker-free transitions. Through extensive qualitative and quantitive experiments as well as a user study, we demonstrate the effectiveness of our method and design choices.

We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent compositions across diverse scenes and styles, similar to the versatility and expressiveness offered by text prompts. A key challenge in this task is to preserve the identity of the objects depicted in the input visual prompts, while also generating diverse compositions across different images. To address this challenge, we introduce a new KV-mixed cross-attention mechanism, in which keys and values are learned from distinct visual representations. The keys are derived from an encoder with a small bottleneck for layout control, whereas the values come from a larger bottleneck encoder that captures fine-grained appearance details. By mixing keys and values from these complementary sources, our model preserves the identity of the visual prompts while supporting flexible variations in object arrangement, pose, and composition. During inference, we further propose object-level compositional guidance to improve the method’s identity preservation and layout correctness. Results show that our technique produces diverse scene compositions that preserve the unique characteristics of each visual prompt, expanding the creative potential of text-to-image generation.

Denoising diffusion models excel at generating high-quality images conditioned on text prompts, yet their effectiveness heavily relies on careful guidance during the sampling process. Classifier-Free Guidance (CFG) provides a widely used mechanism for steering generation by setting the guidance scale, which balances image quality and prompt alignment. However, the choice of the guidance scale has a critical impact on the convergence toward a visually appealing and prompt-adherent image. In this work, we propose an annealing guidance scheduler which dynamically adjusts the guidance scale over time based on the conditional noisy signal. By learning a scheduling policy, our method addresses the temperamental behavior of CFG. Empirical results demonstrate that our guidance scheduler significantly enhances image quality and alignment with the text prompt, advancing the performance of text-to-image generation. Notably, our novel scheduler requires no additional activations or memory consumption, and can seamlessly replace the common classifier-free guidance, offering an improved trade-off between prompt alignment and quality.

We introduce a novel representation for learning and generating Computer-Aided Design (CAD) models in the form of boundary representations (B-Reps). Our representation unifies the continuous geometric properties of B-Rep primitives in different orders (e.g., surfaces and curves) and their discrete topological relations in a holistic latent (HoLa) space. This is based on the simple observation that the topological connection between two surfaces is intrinsically tied to the geometry of their intersecting curve. Such a prior allows us to reformulate topology learning in B-Reps as a geometric reconstruction problem in Euclidean space. Specifically, we eliminate the presence of curves, vertices, and all the topological connections in the latent space by learning to distinguish and derive curve geometries from a pair of surface primitives via a neural intersection network. To this end, our holistic latent space is only defined on surfaces but encodes a full B-Rep model, including the geometry of surfaces, curves, vertices, and their topological relations. Our compact and holistic latent space facilitates the design of a first diffusion-based generator to take on a large variety of inputs including point clouds, single/multi-view images, 2D sketches, and text prompts. Our method significantly reduces ambiguities, redundancies, and incoherences among the generated B-Rep primitives, as well as training complexities inherent in prior multi-step B-Rep learning pipelines, while achieving greatly improved validity rate over current state of the art: 82% vs. ≈50%.

Simplified proxy models are commonly used to represent architectural structures, reducing storage requirements and enabling real-time rendering. However, the geometric simplifications inherent in proxies result in a loss of fine color and geometric details, making it essential for textures to compensate for the loss. Preserving the rich texture information from the original dense architectural reconstructions remains a daunting task, particularly when working with unordered RGB photographs. We propose an automated method for generating realistic texture maps for architectural proxy models at the texel level from an unordered collection of registered photographs. Our approach establishes correspondences between texels on a UV map and pixels in the input images, with each texel's color computed as a weighted blend of associated pixel values. Using differentiable rendering, we optimize blending parameters to ensure photometric and perspective consistency, while maintaining seamless texture coherence. Experimental results demonstrate the effectiveness and robustness of our method across diverse architectural models and varying photographic conditions, enabling the creation of high-quality textures that preserve visual fidelity and structural detail.

Each scanner possesses its unique characteristics and exhibits its distinct sampling error distribution. Training a network on a dataset that includes data collected from different scanners is less effective than training it on data specific to a single scanner. Therefore, we present a novel one-shot learning method allowing for edge extraction on point clouds, by learning the specific data distribution of the target point cloud, and thus achieve superior results compared to networks that were trained on general data distributions. More specifically, we present how to train a lightweight network named OSFENet (One-Shot edge Feature Extraction Network), by designing a filtered-KNN-based surface patch representation that supports a one-shot learning framework. Additionally, we introduce an RBF_DoS module, which integrates Radial Basis Function-based Descriptor of the Surface patch, highly beneficial for the edge extraction on point clouds. The advantage of the proposed OSFENet is demonstrated through comparative analyses against 7 baselines on the ABC dataset, and its practical utility is validated by results across diverse real-scanned datasets, including indoor scenes like S3DIS dataset, and outdoor scenes such as the Semantic3D dataset and UrbanBIS dataset.

This paper addresses the challenge of example-based non-stationary texture synthesis. We introduce a novel two-step approach wherein users first modify a reference texture using standard image editing tools, yielding an initial rough target for the synthesis. Subsequently, our proposed method, termed “self-rectification”, automatically refines this target into a coherent, seamless texture, while faithfully preserving the distinct visual characteristics of the reference exemplar. Our method leverages a pretrained diffusion network, and uses self-attention mechanisms, to grad-ually align the synthesized texture with the reference, en-suring the retention of the structures in the provided target. Through experimental validation, our approach ex-hibits exceptional proficiency in handling non-stationary textures, demonstrating significant advancements in texture synthesis when compared to existing state-of-the-art techniques. Code is available at https://github.com/xiaorongjun000/Self-Rectification

A sketch is one of the most intuitive and versatile tools humans use to convey their ideas visually. An animated sketch opens another dimension to the expression of ideas and is widely used by designers for a variety of purposes. Animating sketches is a laborious process, requiring extensive experience and professional design skills. In this work, we present a method that automatically adds motion to a single-subject sketch (hence, “breathing life into it”), merely by providing a text prompt indicating the desired motion. The output is a short animation provided in vector representation, which can be easily edited. Our method does not require extensive training, but instead leverages the motion prior of a large pretrained text-to- video diffusion model using a score-distillation loss to guide the placement of strokes. To promote natural and smooth motion and to better preserve the sketch's appearance, we model the learned motion through two components. The first governs small local deformations and the second controls global affine transformations. Surprisingly, wefind that even models that struggle to generate sketch videos on their own can still serve as a useful backbone for animating abstract representations.

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visu- ally compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique de- signed to establish style alignment among a series of gener- ated images. By employing minimal ‘attention sharing’ during the diffusion process, our method maintains style con- sistency across images within T2I models. This approach allows for the creation of style-consistent images using a reference style through a straightforward inversion operation. Our method's evaluation across diverse styles and text prompts demonstrates high-quality synthesis and fidelity, underscoring its efficacy in achieving consistent style across various inputs.

We introduce Multi-view Ancestral Sampling (MAS), a method for 3D motion generation, using 2D diffusion models that were trained on motions obtained from in-the-wild videos. As such, MAS opens opportunities to exciting and diverse fields of motion previously under-explored as 3D data is scarce and hard to collect. MAS works by simultaneously denoising multiple 2D motion sequences representing different views of the same 3D motion. It ensures consistency across all views at each diffusion step by combining the individual generations into a unified 3D sequence, and projecting it back to the original views. We demonstrate MAS on 2D pose data acquired from videos depicting professional basketball maneuvers, rhythmic gymnastic performances featuring a ball apparatus, and horse races. In each of these domains, 3D motion capture is arduous, and yet, MAS generates diverse and realistic 3D sequences. Unlike the Score Distillation approach, which optimizes each sample by repeatedly applying small fixes, our method uses a sampling process that was constructed for the diffusion framework. As we demonstrate, MAS avoids common issues such as out-of-domain sampling and mode-collapse. https://guytevet.github.io/mas-page/

This paper addresses the challenge of learning a local visual pattern of an object from one image, and generating images depicting objects with that pattern. Learning a localized concept and placing it on an object in a target image is a nontrivial task, as the objects may have different orientations and shapes. Our approach builds upon recent advancements in visual concept learning. It involves ac-quiring a visual concept (e.g., an ornament) from a source image and subsequently applying it to an object (e.g., a chair) in a target image. Our key idea is to perform in-context concept learning, acquiring the local visual concept within the broader context of the objects they belong to. To localize the concept learning, we employ soft masks that contain both the concept within the mask and the surrounding image area. We demonstrate our approach through object generation within an image, showcasing plausible embedding of in-context learned concepts. We also introduce methods for directing acquired concepts to specific locations within target images, employing cross-attention mechanisms, and establishing correspondences between source and target objects. The effectiveness of our method is demonstrated through quantitative and qualitative experiments, along with comparisons against baseline techniques.

Advancements in 3D instance segmentation have tra-ditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories. Recent efforts have sought to har-ness vision-language models like CLIP for open-set semantic reasoning, yet these methods struggle to distinguish between objects of the same categories and rely on specific prompts that are not universally applicable. In this paper, we introduce SAI3D, a novel zero-shot 3D instance segmentation approach that synergistically leverages geometric priors and semantic cues derived from Segment Any-thing Model (SAM). Our method partitions a 3D scene into geometric primitives, which are then progressively merged into 3D instance segmentations that are consistent with the multi-view SAM masks. Moreover, we design a hierarchi-cal region-growing algorithm with a dynamic thresholding mechanism, which largely improves the robustness of fine-grained 3D scene parsing. Empirical evaluations on Scan-Net, Matterport3D and the more challenging ScanNet++ datasets demonstrate the superiority of our approach. No-tably, SAI3D outperforms existing open-vocabulary base-lines and even surpasses fully-supervised methods in class-agnostic segmentation on ScanNet++. Our project page is at https://yd-yin.github.io/SAI3D.

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the necessity for large Classifier-Free Guidance (CFG) scales, rooted in the distillation of an undesired noise term. Building upon our interpretation, we propose a novel Noise-Free Score Distillation (NFSD) process, which requires minimal modifications to the original SDS framework. Through this streamlined design, we achieve more effective distillation of pre-trained text-to-image diffusion models while using a nominal CFG scale. This strategic choice allows us to prevent the over-smoothing of results, ensuring that the generated data is both realistic and complies with the desired prompt. To demonstrate the efficacy of NFSD, we provide qualitative examples that compare NFSD and SDS, as well as several other methods.

Synthesizing realistic animations of humans, animals, and even imaginary creatures, has long been a goal for artists and computer graphics professionals. Compared to the imaging domain, which is rich with large available datasets, the number of data instances for the motion domain is limited, particularly for the animation of animals and exotic creatures (e.g., dragons), which have unique skeletons and motion patterns. In this work, we introduce SinMDM, a Single Motion Diffusion Model. It is designed to learn the internal motifs of a single motion sequence with arbitrary topology and synthesize a variety of motions of arbitrary length that remain faithful to the learned motifs. We harness the power of diffusion models and present a denoising network explicitly designed for the task of learning from a single input motion. SinMDM is crafted as a lightweight architecture, which avoids overfitting by using a shallow network with local attention layers that narrow the receptive field and encourage motion diversity. Our work applies to multiple contexts, including spatial and temporal in-betweening, motion expansion, style transfer, and crowd animation. Our results show that SinMDM outperforms existing methods both qualitatively and quantitatively. Moreover, while prior network-based approaches require additional training for different applications, SinMDM supports these applications during inference. Our project page, which includes links to the code and trained models, is accessible at https://sinmdm.github.io/SinMDM-page.

Abstract We present SENS, a novel method for generating and editing 3D models from hand‐drawn sketches, including those of abstract nature. Our method allows users to quickly and easily sketch a shape, and then maps the sketch into the latent space of a part‐aware neural implicit shape architecture. SENS analyzes the sketch and encodes its parts into ViT patch encoding, subsequently feeding them into a transformer decoder that converts them to shape embeddings suitable for editing 3D neural implicit shapes. SENS provides intuitive sketch‐based generation and editing, and also succeeds in capturing the intent of the user's sketch to generate a variety of novel and expressive 3D shapes, even from abstract and imprecise sketches. Additionally, SENS supports refinement via part reconstruction, allowing for nuanced adjustments and artifact removal. It also offers part‐based modeling capabilities, enabling the combination of features from multiple sketches to create more complex and customized 3D shapes. We demonstrate the effectiveness of our model compared to the state‐of‐the‐art using objective metric evaluation criteria and a user study, both indicating strong performance on sketches with a medium level of abstraction. Furthermore, we showcase our method's intuitive sketch‐based shape editing capabilities, and validate it through a usability study.

This study introduces CLIP-Flow, a novel network for generating images from a given image or text. To effectively utilize the rich semantics contained in both modalities, we designed a semantics-guided methodology for image- and text-to-image synthesis. In particular, we adopted Contrastive Language-Image Pretraining (CLIP) as an encoder to extract semantics and StyleGAN as a decoder to generate images from such information. Moreover, to bridge the embedding space of CLIP and latent space of StyleGAN, real NVP is employed and modified with activation normalization and invertible convolution. As the images and text in CLIP share the same representation space, text prompts can be fed directly into CLIP-Flow to achieve text-to-image synthesis. We conducted extensive experiments on several datasets to validate the effectiveness of the proposed image-to-image synthesis method. In addition, we tested on the public dataset Multi-Modal CelebA-HQ, for text-to-image synthesis. Experiments validated that our approach can generate high-quality text-matching images, and is comparable with state-of-the-art methods, both qualitatively and quantitatively.

A thin shell model refers to a surface or structure, where the object’s thickness is considered negligible. In the context of 3D printing, thin shell models are characterized by having lightweight, hollow structures, and reduced material usage. Their versatility and visual appeal make them popular in various fields, such as cloth simulation, character skinning, and for thin-walled structures like leaves, paper, or metal sheets. Nevertheless, optimization of thin shell models without external support remains a challenge due to their minimal interior operational space. For the same reasons, hollowing methods are also unsuitable for this task. In fact, thin shell modulation methods are required to preserve the visual appearance of a two-sided surface which further constrain the problem space. In this paper, we introduce a new visual disparity metric tailored for shell models, integrating local details and global shape attributes in terms of visual perception. Our method modulates thin shell models using global deformations and local thickening while accounting for visual saliency, stability, and structural integrity. Thereby, thin shell models such as bas-reliefs, hollow shapes, and cloth can be stabilized to stand in arbitrary orientations, making them ideal for 3D printing.

We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models which involves a two-step process: it first applies a spatial partitioning , referred to as the "split", followed by a "fit" operation to derive a single primitive within each partition. Specifically, our partitioning aims to produce the classical Voronoi diagram of the set of ground-truth (GT) B-Rep primitives. In contrast to prior B-Rep constructions which were bottom-up, either via direct primitive fitting or point clustering, our Split-and-Fit approach is top-down and structure-aware , since a Voronoi partition explicitly reveals both the number of and the connections between the primitives. We design a neural network to predict the Voronoi diagram from an input point cloud or distance field via a binary classification. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data and exhibits superior generalization capabilities. Extensive experiments and evaluation demonstrate that the resulting B-Reps, consisting of parametric surfaces, curves, and vertices, are more plausible than those obtained by existing alternatives, with significant improvements in reconstruction quality. Code will be released on https://github.com/yilinliu77/NVDNet.

Recent text-to-image generative models have enabled us to transform our words into vibrant, captivating imagery. The surge of personalization techniques that has followed has also allowed us to imagine unique concepts in new scenes. However, an intriguing question remains: How can we generate a new , imaginary concept that has never been seen before? In this article, we present the task of creative text-to-image generation , where we seek to generate new members of a broad category (e.g., generating a pet that differs from all existing pets). We leverage the under-studied Diffusion Prior models and show that the creative generation problem can be formulated as an optimization process over the output space of the diffusion prior, resulting in a set of “prior constraints.” To keep our generated concept from converging into existing members, we incorporate a question-answering Vision-Language Model that adaptively adds new constraints to the optimization problem, encouraging the model to discover increasingly more unique creations. Finally, we show that our prior constraints can also serve as a strong mixing mechanism allowing us to create hybrids between generated concepts, introducing even more flexibility into the creative process.

Visually encoding quantitative information associated with graph links is an important problem in graph visualization. A conventional approach is to vary the thickness of lines to encode the strength of connections in node-link diagrams. In this paper, we present Sticky Links, a novel visual encoding method that draws graph links with stickiness. Taking the metaphor of links with glues, sticky links represent connection strength using spiky shapes, ranging from two broken spikes for weak connections to connected lines for strong connections. We conducted a controlled user study to compare the efficiency and aesthetic appeal of stickiness with conventional thickness encoding. Our results show that stickiness enables more effective and expressive quantitative encoding while maintaining the perception of node connectivity. Participants also found sticky links to be more aesthetic and less visually cluttering than conventional thickness encoding. Overall, our findings suggest that sticky links offer a promising alternative to conventional methods for encoding quantitative information in graphs.

Text-guided image generation has progressed rapidly in recent years, inspiring major breakthroughs in text-guided shape generation. Recently, it has been shown that using score distillation, one can successfully text-guide a NeRF model to generate a 3D object. We adapt the score distillation to the publicly available, and computationally efficient, Latent Diffusion Models, which apply the entire diffusion process in a compact latent space of a pretrained autoencoder. As NeRFs operate in image space, a naive solution for guiding them with latent score distillation would require encoding to the latent space at each guidance step. Instead, we propose to bring the NeRF to the latent space, resulting in a Latent-NeRF. Analyzing our Latent-NeRF, we show that while Text-to-3D models can generate impressive results, they are inherently unconstrained and may lack the ability to guide or enforce a specific 3D structure. To assist and direct the 3D generation, we propose to guide our Latent-NeRF using a Sketch-Shape: an abstract geometry that defines the coarse structure of the desired object. Then, we present means to integrate such a constraint directly into a Latent-NeRF. This unique combination of text and shape guidance allows for increased control over the generation process. We also show that latent score distillation can be successfully applied directly on 3D meshes. This allows for generating high-quality textures on a given geometry. Our experiments validate the power of our different forms of guidance and the efficiency of using latent rendering.

Recent large-scale text-guided diffusion models provide powerful image generation capabilities. Currently, a massive effort is given to enable the modification of these images using text only as means to offer intuitive and versatile editing tools. To edit a real image using these state-of-the-art tools, one must first invert the image with a meaningful text prompt into the pretrained model's domain. In this paper, we introduce an accurate inversion technique and thus facilitate an intuitive text-based modification of the image. Our proposed inversion consists of two key novel components: (i) Pivotal inversion for diffusion models. While current methods aim at mapping random noise samples to a single input image, we use a single pivotal noise vector for each timestamp and optimize around it. We demonstrate that a direct DDIM inversion is inadequate on its own, but does provide a rather good anchor for our optimization. (ii) Null-text optimization, where we only modify the unconditional textual embedding that is used for classifier-free guidance, rather than the input text embedding. This allows for keeping both the model weights and the conditional embedding intact and hence enables applying prompt-based editing while avoiding the cumbersome tuning of the model's weights. Our null-text inversion, based on the publicly available Stable Diffusion model, is extensively evaluated on a variety of images and various prompt editing, showing high-fidelity editing of real images.

Can one inject new concepts into an already trained generative model, while respecting its existing structure and knowledge? We propose a new task - domain expansion - to address this. Given a pretrained generator and novel (but related) domains, we expand the generator to jointly model all domains, old and new, harmoniously. First, we note the generator contains a meaningful, pretrained latent space. Is it possible to minimally perturb this hard-earned representation, while maximally representing the new domains? Interestingly, we find that the latent space offers unused, “dormant” directions, which do not affect the output. This provides an opportunity: By “repurposing” these directions, we can represent new domains without perturbing the original representation. In fact, we find that pretrained generators have the capacity to add several- even hundreds - of new domains! Using our expansion method, one “expanded” model can supersede numerous domain-specific models, without expanding the model size. Additionally, a single expanded generator natively supports smooth transitions between domains, as well as composition of domains. Code and project page available here.

The emergence of neural networks has revolutionized the field of motion synthesis. Yet, learning to unconditionally synthesize motions from a given distribution remains challenging, especially when the motions are highly diverse. In this work, we present MoDi - a generative model trained in an unsupervised setting from an extremely diverse, unstructured and unlabeled dataset. During inference, MoDi can synthesize high-quality, diverse motions. Despite the lack of any structure in the dataset, our model yields a well-behaved and highly structured latent space, which can be semantically clustered, constituting a strong motion prior that facilitates various applications including semantic editing and crowd animation. In addition, we present an encoder that inverts real motions into MoDi's natural motion manifold, issuing solutions to various ill-posed challenges such as completion from prefix and spatial editing. Our qualitative and quantitative experiments achieve state-of-the-art results that outperform recent SOTA techniques. Code and trained models are available at https://sigal-raab.github.io/MoDi.

This paper introduces Delta Denoising Score (DDS) a novel diffusion-based scoring technique which optimizes a parametric model for the task of image editing. Unlike the existing Score Distillation Sampling (SDS), which queries the generative model with a single image-text pair, DDS utilizes an additional fixed query of a reference image-text pair to generate delta scores that represent the difference between the outputs of the two queries. By estimating noisy gradient directions introduced by SDS using the source image and its text description, DDS provides cleaner gradient directions that modify the edited portions of the image while leaving others unchanged, thereby yielding a distilled edit of the source image. The analysis presented in this paper supports the power of the new score for image-to-image translation. We further show that the new score can be used to train an effective zero-shot image translation model. The experimental results show that the proposed loss term outperforms existing methods in terms of stability and quality, highlighting its potential for real-world applications.

Text-to-image diffusion models are gradually introduced into computer graphics, recently enabling the development of Text-to-3D pipelines in an open domain. However, for interactive editing purposes, local manipulations of content through a simplistic textual interface can be arduous. Incorporating user guided sketches with Text-to-image pipelines offers users more intuitive control. Still, as state-of-the-art Text-to-3D pipelines rely on optimizing Neural Radiance Fields (NeRF) through gradients from arbitrary rendering views, conditioning on sketches is not straightforward. In this paper, we present SKED, a technique for editing 3D shapes represented by NeRFs. Our technique utilizes as few as two guiding sketches from different views to alter an existing neural field. The edited region respects the prompt semantics through a pre-trained diffusion model. To ensure the generated output adheres to the provided sketches, we propose novel loss functions to generate the desired edits while preserving the density and radiance of the base instance. We demonstrate the effectiveness of our proposed method through several qualitative and quantitative experiments. https://sked-paper.github.io/

Text-to-image models give rise to workflows which often begin with an exploration step, where users sift through a large collection of generated images. The global nature of the text-to-image generation process prevents users from narrowing their exploration to a particular object in the image. In this paper, we present a technique to generate a collection of images that depicts variations in the shape of a specific object, enabling an object-level shape exploration process. Creating plausible variations is challenging as it requires control over the shape of the generated object while respecting its semantics. A particular challenge when generating object variations is accurately localizing the manipulation applied over the object’s shape. We introduce a prompt-mixing technique that switches between prompts along the denoising process to attain a variety of shape choices. To localize the image-space operation, we present two techniques that use the self-attention layers in conjunction with the cross-attention layers. Moreover, we show that these localization techniques are general and effective beyond the scope of generating object variations. Extensive results and comparisons demonstrate the effectiveness of our method in generating object variations, and the competence of our localization techniques.

In this paper, we present a method for converting a given scene image into a sketch using different types and multiple levels of abstraction. We distinguish between two types of abstraction. The first considers the fidelity of the sketch, varying its representation from a more precise portrayal of the input to a looser depiction. The second is defined by the visual simplicity of the sketch, moving from a detailed depiction to a sparse sketch. Using an explicit disentanglement into two abstraction axes — and multiple levels for each one — provides users additional control over selecting the desired sketch based on their personal goals and preferences. To form a sketch at a given level of fidelity and simplification, we train two MLP networks. The first network learns the desired placement of strokes, while the second network learns to gradually remove strokes from the sketch without harming its recognizability and semantics. Our approach is able to generate sketches of complex scenes including those with complex backgrounds (e.g. natural and urban settings) and subjects (e.g. animals and people) while depicting gradual abstractions of the input scene in terms of fidelity and simplicity. https://clipascene.github.io/CLIPascene/

Visual Emotion Analysis (VEA) aims at predicting people’s emotional responses to visual stimuli. This is a promising, yet challenging, task in affective computing, which has drawn increasing attention in recent years. Most of the existing work in this area focuses on feature design, while little attention has been paid to dataset construction. In this work, we introduce EmoSet, the first large-scale visual emotion dataset annotated with rich attributes, which is superior to existing datasets in four aspects: scale, annotation richness, diversity, and data balance. EmoSet comprises 3.3 million images in total, with 118,102 of these images carefully labeled by human annotators, making it five times larger than the largest existing dataset. EmoSet includes images from social networks, as well as artistic images, and it is well balanced between different emotion categories. Motivated by psychological studies, in addition to emotion category, each image is also annotated with a set of describable emotion attributes: brightness, colorfulness, scene type, object class, facial expression, and human action, which can help understand visual emotions in a precise and interpretable way. The relevance of these emotion attributes is validated by analyzing the correlations between them and visual emotion, as well as by designing an attribute module to help visual emotion recognition. We be lieve EmoSet will bring some key insights and encourage further research in visual emotion analysis and understanding. Project page: https://vcc.tech/EmoSet.

Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts. Recently, encoder-based techniques have emerged as a new effective approach for T2I personalization, reducing the need for multiple images and long training times. However, most existing encoders are limited to a single-class domain, which hinders their ability to handle diverse concepts. In this work, we propose a domain-agnostic method that does not require any specialized dataset or prior information about the personalized concepts. We introduce a novel contrastive-based regularization technique to maintain high fidelity to the target concept characteristics while keeping the predicted embeddings close to editable regions of the latent space, by pushing the predicted tokens toward their nearest existing CLIP tokens. Our experimental results demonstrate the effectiveness of our approach and show how the learned tokens are more semantic than tokens predicted by unregularized models. This leads to a better representation that achieves state-of-the-art performance while being more flexible than previous methods.

Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images with variations in backgrounds and poses, and struggle when adapted to a different scenario. In this work, we introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method.

Abstract Despite recent advances in geometric modelling, 3D mesh modelling still involves a considerable amount of manual labour by experts. In this paper, we introduce Mesh Draping: a neural method for transferring existing mesh structure from one shape to another. The method drapes the source mesh over the target geometry and at the same time seeks to preserve the carefully designed characteristics of the source mesh. At its core, our method deforms the source mesh using progressive positional encoding (PE). We show that by leveraging gradually increasing frequencies to guide the neural optimization, we are able to achieve stable and high‐quality mesh transfer. Our approach is simple and requires little user guidance, compared to contemporary surface mapping techniques which rely on parametrization or careful manual tuning. Most importantly, Mesh Draping is a parameterization‐free method, and thus applicable to a variety of target shape representations, including point clouds, polygon soups and non‐manifold meshes. We demonstrate that the transferred meshing remains faithful to the source mesh design characteristics, and at the same time fits the target geometry well.

A key aspect of text-to-image personalization methods is the manner in which the target concept is represented within the generative process. This choice greatly affects the visual fidelity, downstream editability, and disk space needed to store the learned concept. In this paper, we explore a new text-conditioning space that is dependent on both the denoising process timestep (time) and the denoising U-Net layers (space) and showcase its compelling properties. A single concept in the space-time representation is composed of hundreds of vectors, one for each combination of time and space , making this space challenging to optimize directly. Instead, we propose to implicitly represent a concept in this space by optimizing a small neural mapper that receives the current time and space parameters and outputs the matching token embedding. In doing so, the entire personalized concept is represented by the parameters of the learned mapper, resulting in a compact, yet expressive, representation. Similarly to other personalization methods, the output of our neural mapper resides in the input space of the text encoder. We observe that one can significantly improve the convergence and visual fidelity of the concept by introducing a textual bypass , where our neural mapper additionally outputs a residual that is added to the output of the text encoder. Finally, we show how one can impose an importance-based ordering over our implicit representation, providing users control over the reconstruction and editability of the learned concept using a single trained model. We demonstrate the effectiveness of our approach over a range of concepts and prompts, showing our method's ability to generate high-quality and controllable compositions without fine-tuning any parameters of the generative model itself.

Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect , where the model fails to generate one or more of the subjects from the input prompt. Moreover, we find that in some cases the model also fails to correctly bind attributes ( e.g. , colors) to their corresponding subjects. To help mitigate these failure cases, we introduce the concept of Generative Semantic Nursing (GSN) , where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness of the generated images. Using an attention-based formulation of GSN, dubbed Attend-and-Excite , we guide the model to refine the cross-attention units to attend to all subject tokens in the text prompt and strengthen --- or excite --- their activations, encouraging the model to generate all subjects described in the text prompt. We compare our approach to alternative approaches and demonstrate that it conveys the desired concepts more faithfully across a range of text prompts. Code is available at our project page: https://attendandexcite.github.io/Attend-and-Excite/.

Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle with lengthy training times, high storage requirements or loss of identity. To overcome these limitations, we propose an encoder-based domain-tuning approach. Our key insight is that by underfitting on a large set of concepts from a given domain, we can improve generalization and create a model that is more amenable to quickly adding novel concepts from the same domain. Specifically, we employ two components: First, an encoder that takes as an input a single image of a target concept from a given domain, e.g. a specific face, and learns to map it into a word-embedding representing the concept. Second, a set of regularized weight-offsets for the text-to-image model that learn how to effectively injest additional concepts. Together, these components are used to guide the learning of unseen concepts, allowing us to personalize a model using only a single image and as few as 5 training steps --- accelerating personalization from dozens of minutes to seconds , while preserving quality. Code and trained encoders will be available at our project page.

A word-as-image is a semantic typography technique where a word illustration presents a visualization of the meaning of the word, while also preserving its readability. We present a method to create word-as-image illustrations automatically. This task is highly challenging as it requires semantic understanding of the word and a creative idea of where and how to depict these semantics in a visually pleasing and legible manner. We rely on the remarkable ability of recent large pretrained language-vision models to distill textual concepts visually. We target simple, concise, black-and-white designs that convey the semantics clearly. We deliberately do not change the color or texture of the letters and do not use embellishments. Our method optimizes the outline of each letter to convey the desired concept, guided by a pretrained Stable Diffusion model. We incorporate additional loss terms to ensure the legibility of the text and the preservation of the style of the font. We show high quality and engaging results on numerous examples and compare to alternative techniques. Code and demo will be available at our project page.

This paper presents a new text-guided technique for generating 3D shapes. The technique leverages a hybrid 3D shape representation, namely EXIM, combining the strengths of explicit and implicit representations. Specifically, the explicit stage controls the topology of the generated 3D shapes and enables local modifications, whereas the implicit stage refines the shape and paints it with plausible colors. Also, the hybrid approach separates the shape and color and generates color conditioned on shape to ensure shape-color consistency. Unlike the existing state-of-the-art methods, we achieve high-fidelity shape generation from natural-language descriptions without the need for time-consuming per-shape optimization or reliance on human-annotated texts during training or test-time optimization. Further, we demonstrate the applicability of our approach to generate indoor scenes with consistent styles using text-induced 3D shapes. Through extensive experiments, we demonstrate the compelling quality of our results and the high coherency of our generated shapes with the input texts, surpassing the performance of existing methods by a significant margin. Codes and models are released at https://github.com/liuzhengzhe/EXIM.

Recently, numerous facial editing techniques have been proposed that leverage the generative power of a pretrained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the pretrained generator’s domain. As it turns out, StyleGAN’s latent space induces an inherent tradeoff between distortion and editability, i.e., between maintaining the original appearance and convincingly altering its attributes. Hence, it remains challenging to apply ID-preserving edits to real facial images. In this article, we present an approach to bridge this gap. The idea is Pivotal Tuning —a brief training process that preserves editing quality, while surgically changing the portrayed identity and appearance. In Pivotal Tuning Inversion, an initial inverted latent code serves as a pivot, around which the generator is fine-tuned. At the same time, a regularization term keeps nearby identities intact, to locally contain the effect. We further show that Pivotal Tuning also applies to accommodating for a multitude of faces, while introducing negligible distortion on the rest of the domain. We validate our technique through inversion and editing metrics and show preferable scores to state-of-the-art methods. Last, we present successful editing for harder cases, including elaborate make-up or headwear.

A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining certain aspects of the concept. Hence, it is often necessary to separate a concept into different aspects to provide new perspectives. In this paper, we propose a method to decompose a visual concept, represented as a set of images, into different visual aspects encoded in a hierarchical tree structure. We utilize large vision-language models and their rich latent space for concept decomposition and generation. Each node in the tree represents a sub-concept using a learned vector embedding injected into the latent space of a pretrained text-to-image model. We use a set of regularizations to guide the optimization of the embedding vectors encoded in the nodes to follow the hierarchical structure of the tree. Our method allows to explore and discover new concepts derived from the original one. The tree provides the possibility of endless visual sampling at each node, allowing the user to explore the hidden sub-concepts of the object of interest. The learned aspects in each node can be combined within and across trees to create new visual ideas, and can be used in natural language sentences to apply such aspects to new designs. Project page: https://inspirationtree.github.io/inspirationtree/

Synthesizing human motion with a global structure, such as a choreography, is a challenging task. Existing methods tend to concentrate on local smooth pose transitions and neglect the global context or the theme of the motion. In this work, we present a music-driven motion synthesis framework that generates long-term sequences of human motions which are synchronized with the input beats, and jointly form a global structure that respects a specific dance genre. In addition, our framework enables generation of diverse motions that are controlled by the content of the music, and not only by the beat. Our music-driven dance synthesis framework is a hierarchical system that consists of three levels: pose, motif, and choreography. The pose level consists of an LSTM component that generates temporally coherent sequences of poses. The motif level guides sets of consecutive poses to form a movement that belongs to a specific distribution using a novel motion perceptual-loss. And the choreography level selects the order of the performed movements and drives the system to follow the global structure of a dance genre. Our results demonstrate the effectiveness of our music-driven framework to generate natural and consistent movements on various dance types, having control over the content of the synthesized motions, and respecting the overall structure of the dance.

We propose a novel method for solving regression tasks using few-shot or weak supervision. At the core of our method is the fundamental observation that GANs are incredibly successful at encoding semantic information within their latent space, even in a completely unsupervised setting. For modern generative frameworks, this semantic encoding manifests as smooth, linear directions which affect image attributes in a disentangled manner. These directions have been widely used in GAN-based image editing. In this work, we leverage them for few-shot regression. Specifically, we make the simple observation that distances traversed along such directions are good features for downstream tasks - reliably gauging the magnitude of a property in an image. In the absence of explicit supervision, we use these distances to solve tasks such as sorting a collection of images, and ordinal regression. With a few labels - as little as two - we calibrate these distances to real-world values and convert a pre-trained GAN into a state-of-the-art few-shot regression model. This enables solving regression tasks on datasets and attributes which are difficult to produce quality supervision for. Extensive experimental evaluations demonstrate that our method can be applied across a wide range of domains, leverage multiple latent direction discovery frame-works, and achieve state-of-the-art results in few-shot and low-supervision settings, even when compared to methods designed to tackle a single task. Code is available on our project website.

We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each exhibiting plausible shape details while being faithful to the input. To facilitate the use of transformers for 3D, we introduce a compact 3D representation, vector quantized deep implicit function (VQDIF), that utilizes spatial sparsity to represent a close approximation of a 3D shape by a short sequence of discrete variables. Experiments demonstrate that ShapeFormer outperforms prior art for shape completion from ambiguous partial inputs in terms of both completion quality and diversity. We also show that our approach effectively handles a variety of shape types, incomplete patterns, and real-world scans.

The ability of Generative Adversarial Networks to encode rich semantics within their latent space has been widely adopted for facial image editing. However, replicating their success with videos has proven challenging. Applying StyleGAN editing to real videos introduces two main challenges: (i) StyleGAN operates over aligned crops. When editing videos, these crops need to be pasted back into the frame, resulting in a spatial inconsistency. (ii) Videos introduce a fundamental barrier to overcome — temporal coherency. To address the first challenge, we propose a novel stitching-tuning procedure. The generator is carefully tuned to overcome the spatial artifacts at crop borders, resulting in smooth transitions even when difficult backgrounds are involved. Turning to temporal coherence, we propose that this challenge is largely artificial. The source video is already temporally coherent, and deviations arise in part due to careless treatment of individual components in the editing pipeline. We leverage the natural alignment of StyleGAN and the tendency of neural networks to learn low-frequency functions, and demonstrate that they provide a strongly consistent prior. These components are combined in an end-to-end framework for semantic editing of facial videos. We compare our pipeline to the current state-of-the-art and demonstrate significant improvements. Our method produces meaningful manipulations and maintains greater spatial and temporal consistency, even on challenging talking head videos which current methods struggle with. Our code and videos are available at https://stitch-time.github.io/.

Abstract Generative Adversarial Networks (GANs) have established themselves as a prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability to support a large array of downstream tasks. This state‐of‐the‐art report covers the StyleGAN architecture, and the ways it has been employed since its conception, while also analyzing its severe limitations. It aims to be of use for both newcomers, who wish to get a grasp of the field, and for more experienced readers that might benefit from seeing current research trends and existing tools laid out. Among StyleGAN's most interesting aspects is its learned latent space. Despite being learned with no supervision, it is surprisingly well‐behaved and remarkably disentangled. Combined with StyleGAN's visual quality, these properties gave rise to unparalleled editing capabilities. However, the control offered by StyleGAN is inherently limited to the generator's learned distribution, and can only be applied to images generated by StyleGAN itself. Seeking to bring StyleGAN's latent control to real‐world scenarios, the study of GAN inversion and latent space embedding has quickly gained in popularity. Meanwhile, this same study has helped shed light on the inner workings and limitations of StyleGAN. We map out StyleGAN's impressive story through these investigations, and discuss the details that have made StyleGAN the go‐to generator. We further elaborate on the visual priors StyleGAN constructs, and discuss their use in downstream discriminative tasks. Looking forward, we point out StyleGAN's limitations and speculate on current trends and promising directions for future research, such as task and target specific fine‐tuning.

Abstract Synthesizing novel views of dynamic humans from stationary monocular cameras is a specialized but desirable setup. This is particularly attractive as it does not require static scenes, controlled environments, or specialized capture hardware. In contrast to techniques that exploit multi‐view observations, the problem of modeling a dynamic scene from a single view is significantly more under‐constrained and ill‐posed. In this paper, we introduce Neural Motion Consensus Flow (MoCo‐Flow), a representation that models dynamic humans in stationary monocular cameras using a 4D continuous time‐variant function. We learn the proposed representation by optimizing for a dynamic scene that minimizes the total rendering error, over all the observed images. At the heart of our work lies a carefully designed optimization scheme, which includes a dedicated initialization step and is constrained by a motion consensus regularization on the estimated motion flow. We extensively evaluate MoCo‐Flow on several datasets that contain human motions of varying complexity, and compare, both qualitatively and quantitatively, to several baselines and ablated variations of our methods, showing the efficacy and merits of the proposed approach. Pretrained model, code, and data will be released for research purposes upon paper acceptance.

Abstract In this work, we present our strategy for camera control in dynamic scenes with multiple people (sports teams). We learn a generic model of the player dynamics offline in simulation. We use only a few sparse demonstrations of a user's camera control policy to learn a reward function to drive camera motion in an ongoing dynamic scene. Key to our approach is the creation of a low‐dimensional representation of the scene dynamics which is independent of the environment action and rewards, which enables learning the reward function using only a small number of examples. We cast the user‐specific control objective as an inverse reinforcement learning problem, aiming to learn an expert's intention from a small number of demonstrations. The learned reward function is used in combination with a visual model predictive controller (MPC). We learn a generic scene dynamics model that is agnostic to the user‐specific reward, enabling reusing the same dynamics model for different camera control policies. We show the effectiveness of our method on simulated and real soccer matches.

Abstract We present a technique for visualizing point clouds using a neural network. Our technique allows for an instant preview of any point cloud, and bypasses the notoriously difficult surface reconstruction problem or the need to estimate oriented normals for splat‐based rendering. We cast the preview problem as a conditional image‐to‐image translation task, and design a neural network that translates point depth‐map directly into an image, where the point cloud is visualized as though a surface was reconstructed from it. Furthermore, the resulting appearance of the visualized point cloud can be, optionally, conditioned on simple control variables (e.g., color and light). We demonstrate that our technique instantly produces plausible images, and can, on‐the‐fly effectively handle noise, non‐uniform sampling, and thin surfaces sheets.

Abstract In unsupervised video retargeting, content is transferred from one video to another while preserving the original appearance and style, without any additional annotations. While this challenge has seen substantial advancements through the use of deep neural networks, current methods struggle when the source and target videos are of shapes that are different in limb lengths or other body proportions. In this work, we consider this task for the case of objects of different shapes and appearances, that consist of similar skeleton connectivity and depict similar motion. We introduce JOKR—a JOint Keypoint Representation that captures the geometry common to both videos, while being disentangled from their unique styles. Our model first extracts unsupervised keypoints from the given videos. From this representation, two decoders reconstruct geometry and appearance, one for each of the input sequences. By employing an affine‐invariant domain confusion term over the keypoints bottleneck, we enforce the unsupervised keypoint representations of both videos to be indistinguishable. This encourages the aforementioned disentanglement between motion and appearance, mapping similar poses from both domains to the same representation. This allows yielding a sequence with the appearance and style of one video, but the content of the other. Our applicability is demonstrated through challenging video pairs compared to state‐of‐the‐art methods. Furthermore, we demonstrate that this geometry‐driven representation enables intuitive control, such as temporal coherence and manual pose editing. Videos can be viewed in the supplement HTML.

Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a different 2D kernel. The composition of the two convolutions constitutes an over-parameterization, since it adds learnable parameters, while the resulting linear operation can be expressed by a single convolution layer. We refer to this depthwise over-parameterized convolutional layer as DO-Conv, which is a novel way of over-parameterization. We show with extensive experiments that the mere replacement of conventional convolutional layers with DO-Conv layers boosts the performance of CNNs on many classical vision tasks, such as image classification, detection, and segmentation. Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization. As DO-Conv introduces performance gains without incurring any computational complexity increase for inference, we advocate it as an alternative to the conventional convolutional layer. We open sourced an implementation of DO-Conv in Tensorflow, PyTorch and GluonCV at https://github.com/yangyanli/DO-Conv.

Can a generative model be trained to produce images from a specific domain, guided only by a text prompt, without seeing any image? In other words: can an image generator be trained "blindly"? Leveraging the semantic power of large scale Contrastive-Language-Image-Pre-training (CLIP) models, we present a text-driven method that allows shifting a generative model to new domains, without having to collect even a single image. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains characterized by diverse styles and shapes. Notably, many of these modifications would be difficult or infeasible to reach with existing methods. We conduct an extensive set of experiments across a wide range of domains. These demonstrate the effectiveness of our approach, and show that our models preserve the latent-space structure that makes generative models appealing for downstream tasks. Code and videos available at: stylegan-nada.github.io/

Neural implicit fields are quickly emerging as an attractive representation for learning based techniques. However, adopting them for 3D shape modeling and editing is challenging. We introduce a method for E diting I mplicit S hapes T hrough P art A ware G enera T ion, permuted in short as SPAGHETTI. Our architecture allows for manipulation of implicit shapes by means of transforming, interpolating and combining shape segments together, without requiring explicit part supervision. SPAGHETTI disentangles shape part representation into extrinsic and intrinsic geometric information. This characteristic enables a generative framework with part-level control. The modeling capabilities of SPAGHETTI are demonstrated using an interactive graphical interface, where users can directly edit neural implicit shapes. Our code, editing user interface demo and pre-trained models are available at github.com/amirhertz/spaghetti.

We present StyleFusion , a new mapping architecture for StyleGAN, which takes as input a number of latent codes and fuses them into a single style code. Inserting the resulting style code into a pre-trained StyleGAN generator results in a single harmonized image in which each semantic region is controlled by one of the input latent codes. Effectively, StyleFusion yields a disentangled representation of the image, providing fine-grained control over each region of the generated image. Moreover, to help facilitate global control over the generated image, a special input latent code is incorporated into the fused representation. StyleFusion operates in a hierarchical manner, where each level is tasked with learning to disentangle a pair of image regions (e.g., the car body and wheels). The resulting learned disentanglement allows one to modify both local, fine-grained semantics (e.g., facial features) as well as more global features (e.g., pose and background), providing improved flexibility in the synthesis process. As a natural extension, StyleFusion allows one to perform semantically-aware cross-image mixing of regions that are not necessarily aligned. Finally, we demonstrate how StyleFusion can be paired with existing editing techniques to more faithfully constrain the edit to the user’s region of interest. Code is available at: https://github.com/OmerKafri/StyleFusion .

We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output is faithful to the person's key facial characteristics. Given a small reference set of portrait images of a person (~ 100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space. We show that this manifold constitutes a personalized region that spans latent codes associated with diverse portrait images of the individual. Moreover, we demonstrate that we obtain a personalized generative prior, and propose a unified approach to apply it to various ill-posed image enhancement problems, such as inpainting and super-resolution, as well as semantic editing. Using the personalized generative prior we obtain outputs that exhibit high-fidelity to the input images and are also faithful to the key facial characteristics of the individual in the reference set. We demonstrate our method with fair-use images of numerous widely recognizable individuals for whom we have the prior knowledge for a qualitative evaluation of the expected outcome. We evaluate our approach against few-shots baselines and show that our personalized prior, quantitatively and qualitatively, outperforms state-of-the-art alternatives.

Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings. Abstraction entails identifying the essential visual properties of an object or scene, which requires semantic understanding and prior knowledge of high-level concepts. Abstract depictions are therefore challenging for artists, and even more so for machines. We present CLIPasso, an object sketching method that can achieve different levels of abstraction, guided by geometric and semantic simplifications. While sketch generation methods often rely on explicit sketch datasets for training, we utilize the remarkable ability of CLIP (Contrastive-Language-Image-Pretraining) to distill semantic concepts from sketches and images alike. We define a sketch as a set of Bézier curves and use a differentiable rasterizer to optimize the parameters of the curves directly with respect to a CLIP-based perceptual loss. The abstraction degree is controlled by varying the number of strokes. The generated sketches demonstrate multiple levels of abstraction while maintaining recognizability, underlying structure, and essential visual components of the subject drawn.

Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this article, we introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. To alleviate inevitable global information loss caused by the rotation-invariant representations, we further introduce a region relation convolution to encode local and non-local information. We evaluate our method on multiple point cloud analysis tasks, including (i) shape classification, (ii) part segmentation, and (iii) shape retrieval. Extensive experimental results show that our method achieves consistent, and also the best performance, on inputs at arbitrary orientations, compared with all the state-of-the-art methods.

Static visual attributes such as color and shape are used with great success in visual charts designed to be displayed in static, hard-copy form. However, nowadays digital displays become ubiquitous in the visualization of any form of data, lifting the confines of static presentations. In this article, we propose incorporating data-driven animations to bring static charts to life, with the purpose of encoding and emphasizing certain attributes of the data. We lay out a design space for data-driven animated effects and experiment with three versatile effects, marching ants, geometry deformation and gradual appearance. For each, we provide practical details regarding their mode of operation and extent of interaction with existing visual encodings. We examine the impact and effectiveness of our enhancements through an empirical user study to assess preference as well as gauge the influence of animated effects on human perception in terms of speed and accuracy of visual understanding.

Rigid registration of partial observations is a fundamental problem in various applied fields. In computer graphics, special attention has been given to the registration between two partial point clouds generated by scanning devices. State-of-the-art registration techniques still struggle when the overlap region between the two point clouds is small, and completely fail if there is no overlap between the scan pairs. In this article, we present a learning-based technique that alleviates this problem, and allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap, a setting that has been referred to as tele-registration. Our technique is based on a novel neural network design that learns a prior of a class of shapes and can complete a partial shape. The key idea is combining the registration and completion tasks in a way that reinforces each other. In particular, we simultaneously train the registration network and completion network using two coupled flows, one that register-and-complete, and one that complete-and-register, and encourage the two flows to produce a consistent result. We show that, compared with each separate flow, this two-flow training leads to robust and reliable tele-registration, and hence to a better point cloud prediction that completes the registered scans. It is also worth mentioning that each of the components in our neural network outperforms state-of-the-art methods in both completion and registration. We further analyze our network with several ablation studies and demonstrate its performance on a large number of partial point clouds, both synthetic and real-world, that have only small or no overlap.

We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style vectors which are fed into a pretrained StyleGAN generator, forming the extended $\mathcal{W} + $ latent space. We first show that our encoder can directly embed real images into $\mathcal{W} + $, with no additional optimization. Next, we propose utilizing our encoder to directly solve image-to-image translation tasks, defining them as encoding problems from some input domain into the latent domain. By deviating from the standard "invert first, edit later" methodology used with previous StyleGAN encoders, our approach can handle a variety of tasks even when the input image is not represented in the StyleGAN domain. We show that solving translation tasks through StyleGAN significantly simplifies the training process, as no adversary is required, has better support for solving tasks without pixel-to-pixel correspondence, and inherently supports multi-modal synthesis via the resampling of styles. Finally, we demonstrate the potential of our framework on a variety of facial image-to-image translation tasks, even when compared to state-of-the-art solutions designed specifically for a single task, and further show that it can be extended beyond the human facial domain. Code is available at https://github.com/eladrich/pixel2style2pixel.

Non-visual imaging sensors are widely used in the industry for different purposes. Those sensors are more expensive than visual (RGB) sensors, and usually produce images with lower resolution. To this end, Cross-Modality Super-Resolution methods were introduced, where an RGB image of a high-resolution assists in increasing the resolution of a low-resolution modality. However, fusing images from different modalities is not a trivial task, since each multi-modal pair varies greatly in its internal correlations. For this reason, traditional state-of-the-arts which are trained on external datasets often struggle with yielding an artifact-free result that is still loyal to the target modality characteristics.We present CMSR, a single-pair approach for Cross-Modality Super-Resolution. The network is internally trained on the two input images only, in a self-supervised manner, learns their internal statistics and correlations, and applies them to up-sample the target modality. CMSR contains an internal transformer which is trained on-the-fly together with the up-sampling process itself and without supervision, to allow dealing with pairs that are only weakly aligned. We show that CMSR produces state-of-the-art super resolved images, yet without introducing artifacts or irrelevant details that originate from the RGB image only.

Recently, the power of unconditional image synthesis has significantly advanced through the use of Generative Adversarial Networks (GANs). The task of inverting an image into its corresponding latent code of the trained GAN is of utmost importance as it allows for the manipulation of real images, leveraging the rich semantics learned by the network. Recognizing the limitations of current inversion approaches, in this work we present a novel inversion scheme that extends current encoder-based inversion methods by introducing an iterative refinement mechanism. Instead of directly predicting the latent code of a given real image using a single pass, the encoder is tasked with predicting a residual with respect to the current estimate of the inverted latent code in a self-correcting manner. Our residual-based encoder, named ReStyle, attains improved accuracy compared to current state-of-the-art encoder-based methods with a negligible increase in inference time. We analyze the behavior of ReStyle to gain valuable insights into its iterative nature. We then evaluate the performance of our residual encoder and analyze its robustness compared to optimization-based inversion and state-of-the-art encoders. Code is available via our project page: https: //yuval-alaluf.github.io/restyle-encoder/

RGB-D semantic segmentation has attracted increasing attention over the past few years. Existing methods mostly employ homogeneous convolution operators to consume the RGB and depth features, ignoring their intrinsic differences. In fact, the RGB values capture the photometric appearance properties in the projected image space, while the depth feature encodes both the shape of a local geometry as well as the base (whereabout) of it in a larger context. Compared with the base, the shape probably is more inherent and has a stronger connection to the semantics, and thus is more critical for segmentation accuracy. Inspired by this observation, we introduce a Shape-aware Convolutional layer (ShapeConv) for processing the depth feature, where the depth feature is firstly decomposed into a shape-component and a base-component, next two learnable weights are introduced to cooperate with them independently, and finally a convolution is applied on the re-weighted combination of these two components. ShapeConv is model-agnostic and can be easily integrated into most CNNs to replace vanilla convolutional layers for semantic segmentation. Extensive experiments on three challenging indoor RGB-D semantic segmentation benchmarks, i.e., NYU-Dv2(-13,-40), SUN RGB-D, and SID, demonstrate the effectiveness of our ShapeConv when employing it over five popular architectures. Moreover, the performance of CNNs with ShapeConv is boosted without introducing any computation and memory increase in the inference phase. The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.

Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of StyleGAN to manipulate generated and real images. However, discovering semantically meaningful latent manipulations typically involves painstaking human examination of the many degrees of freedom, or an annotated collection of images for each desired manipulation. In this work, we explore leveraging the power of recently introduced Contrastive Language-Image Pre-training (CLIP) models in order to develop a text-based interface for StyleGAN image manipulation that does not require such manual effort. We first introduce an optimization scheme that utilizes a CLIP-based loss to modify an input latent vector in response to a user-provided text prompt. Next, we describe a latent mapper that infers a text-guided latent manipulation step for a given input image, allowing faster and more stable text-based manipulation. Finally, we present a method for mapping text prompts to input-agnostic directions in StyleGAN’s style space, enabling interactive text-driven image manipulation. Extensive results and comparisons demonstrate the effectiveness of our approaches.

Multilayer-perceptrons (MLP) are known to struggle learning functions of high-frequencies, and in particular, instances of wide frequency bands.We present a progressive mapping scheme for input signals of MLP networks, enabling them to better fit a wide range of frequencies without sacrificing training stability or requiring any domain specific preprocessing. We introduce Spatially Adaptive Progressive Encoding (SAPE) layers, which gradually unmask signal components with increasing frequencies as a function of time and space. The progressive exposure of frequencies is monitored by a feedback loop throughout the neural optimization process, allowing changes to propagate at different rates among local spatial portions of the signal space. We demonstrate the advantage of our method on variety of domains and applications: regression of low dimensional signals and images, representation learning of occupancy networks, and a geometric task of mesh transfer between 3D shapes.

Abstract In this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in conventional graphics pipeline. To this end, we present Neural Graphics Pipeline (NGP), a hybrid generative model that brings together neural and traditional image formation models. NGP decomposes the image into a set of interpretable appearance feature maps, uncovering direct control handles for controllable image generation. To form an image, NGP generates coarse 3D models that are fed into neural rendering modules to produce view‐specific interpretable 2D maps, which are then composited into the final output image using a traditional image formation model. Our approach offers control over image generation by providing direct handles controlling illumination and camera parameters, in addition to control over shape and appearance variations. The key challenge is to learn these controls through unsupervised training that links generated coarse 3D models with unpaired real images via neural and traditional (e.g., Blinn‐Phong) rendering functions, without establishing an explicit correspondence between them. We demonstrate the effectiveness of our approach on controllable image generation of single‐object scenes. We evaluate our hybrid modeling framework, compare with neural‐only generation methods (namely, DCGAN, LSGAN, WGAN‐GP, VON, and SRNs), report improvement in FID scores against real images, and demonstrate that NGP supports direct controls common in traditional forward rendering. Code is available at http://geometry.cs.ucl.ac.uk/projects/2021/ngp .

Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature space using the deep layers of a neural network containing rich important semantic information. We directly adjust the image feature maps, extracted from a pre-trained classification network, and reconstruct the resized image using neural-network based optimization. This novel approach leverages the hierarchical encoding of the network, and in particular, the high-level discriminative power of its deeper layers, that can recognize semantic regions and objects, thereby allowing maintenance of their aspect ratios. Our use of reconstruction from deep features results in less noticeable artifacts than use of imagespace resizing operators. We evaluate our method on benchmarks, compare it to alternative approaches, and demonstrate its strengths on challenging images.

Humans regularly interact with their surrounding objects. Such interactions often result in strongly correlated motions between humans and the interacting objects. We thus ask: “Is it possible to infer object properties from skeletal motion alone, even without seeing the interacting object itself?” In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone. This inference allows us to disentangle the motion from the object property and transfer object properties to a given motion. We collected a large number of videos and 3D skeletal motions of performing actors using an inertial motion capture device. We analyzed similar actions and learned subtle differences between them to reveal latent properties of the interacting objects. In particular, we learned to identify the interacting object, by estimating its weight, or its spillability. Our results clearly demonstrate that motions and interacting objects are highly correlated and that related object latent properties can be inferred from 3D skeleton sequences alone, leading to new synthesis possibilities for motions involving human interaction. Our dataset is available at http://vcc.szu.edu.cn/research/2020/IT.html .

The task of age transformation illustrates the change of an individual's appearance over time. Accurately modeling this complex transformation over an input facial image is extremely challenging as it requires making convincing, possibly large changes to facial features and head shape, while still preserving the input identity. In this work, we present an image-to-image translation method that learns to directly encode real facial images into the latent space of a pre-trained unconditional GAN (e.g., StyleGAN) subject to a given aging shift. We employ a pre-trained age regression network to explicitly guide the encoder in generating the latent codes corresponding to the desired age. In this formulation, our method approaches the continuous aging process as a regression task between the input age and desired target age, providing fine-grained control over the generated image. Moreover, unlike approaches that operate solely in the latent space using a prior on the path controlling age, our method learns a more disentangled, non-linear path. Finally, we demonstrate that the end-to-end nature of our approach, coupled with the rich semantic latent space of StyleGAN, allows for further editing of the generated images. Qualitative and quantitative evaluations show the advantages of our method compared to state-of-the-art approaches. Code is available at our project page: https://yuval-alaluf.github.io/SAM.

In recent years, considerable progress has been made in the visual quality of Generative Adversarial Networks (GANs). Even so, these networks still suffer from degradation in quality for high-frequency content, stemming from a spectrally biased architecture, and similarly unfavorable loss functions. To address this issue, we present a novel general-purpose Style and WAvelet based GAN (SWAGAN) that implements progressive generation in the frequency domain. SWAGAN incorporates wavelets throughout its generator and discriminator architectures, enforcing a frequency-aware latent representation at every step of the way. This approach, designed to directly tackle the spectral bias of neural networks, yields an improvement in the ability to generate medium and high frequency content, including structures which other networks fail to learn. We demonstrate the advantage of our method by integrating it into the SyleGAN2 framework, and verifying that content generation in the wavelet domain leads to more realistic high-frequency content, even when trained for fewer iterations. Furthermore, we verify that our model's latent space retains the qualities that allow StyleGAN to serve as a basis for a multitude of editing tasks, and show that our frequency-aware approach also induces improved high-frequency performance in downstream tasks.

We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud. Unlike other point up-sampling methods which analyze shapes via local patches, in this work, we learn from global subsets. We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network. Specifically, we define source and target subsets according to the desired consolidation criteria (e.g., generating sharp points or points in sparse regions). The network learns a mapping from source to target subsets, and implicitly learns to consolidate the point cloud. During inference, the network is fed with random subsets of points from the input, which it displaces to synthesize a consolidated point set. We leverage the inductive bias of neural networks to eliminate noise and outliers, a notoriously difficult problem in point cloud consolidation. The shared weights of the network are optimized over the entire shape, learning non-local statistics and exploiting the recurrence of local-scale geometries. Specifically, the network encodes the distribution of the underlying shape surface within a fixed set of local kernels, which results in the best explanation of the underlying shape surface. We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.

Establishing a consistent normal orientation for point clouds is a notoriously difficult problem in geometry processing, requiring attention to both local and global shape characteristics. The normal direction of a point is a function of the local surface neighborhood; yet, point clouds do not disclose the full underlying surface structure. Even assuming known geodesic proximity, calculating a consistent normal orientation requires the global context. In this work, we introduce a novel approach for establishing a globally consistent normal orientation for point clouds. Our solution separates the local and global components into two different sub-problems. In the local phase, we train a neural network to learn a coherent normal direction per patch ( i.e. , consistently oriented normals within a single patch). In the global phase, we propagate the orientation across all coherent patches using a dipole propagation. Our dipole propagation decides to orient each patch using the electric field defined by all previously orientated patches. This gives rise to a global propagation that is stable, as well as being robust to nearby surfaces, holes, sharp features and noise.

We introduce MotioNet , a deep neural network that directly reconstructs the motion of a 3D human skeleton from a monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used motion representation. At the crux of our approach lies a deep neural network with embedded kinematic priors, which decomposes sequences of 2D joint positions into two separate attributes: a single, symmetric skeleton encoded by bone lengths, and a sequence of 3D joint rotations associated with global root positions and foot contact labels. These attributes are fed into an integrated forward kinematics (FK) layer that outputs 3D positions, which are compared to a ground truth. In addition, an adversarial loss is applied to the velocities of the recovered rotations to ensure that they lie on the manifold of natural joint rotations. The key advantage of our approach is that it learns to infer natural joint rotations directly from the training data rather than assuming an underlying model, or inferring them from joint positions using a data-agnostic IK solver. We show that enforcing a single consistent skeleton along with temporally coherent joint rotations constrains the solution space, leading to a more robust handling of self-occlusions and depth ambiguities.

Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the existence of a distortion-editability tradeoff and a distortion-perception tradeoff within the StyleGAN latent space. We then suggest two principles for designing encoders in a manner that allows one to control the proximity of the inversions to regions that StyleGAN was originally trained on. We present an encoder based on our two principles that is specifically designed for facilitating editing on real images by balancing these tradeoffs. By evaluating its performance qualitatively and quantitatively on numerous challenging domains, including cars and horses, we show that our inversion method, followed by common editing techniques, achieves superior real-image editing quality, with only a small reconstruction accuracy drop.

Infographics are engaging visual representations that tell an informative story using a fusion of data and graphical elements. The large variety of infographic design poses a challenge for their high-level analysis. We use the concept of Visual Information Flow (VIF), which is the underlying semantic structure that links graphical elements to convey the information and story to the user. To explore VIF, we collected a repository of over 13K infographics. We use a deep neural network to identify visual elements related to information, agnostic to their various artistic appearances. We construct the VIF by automatically chaining these visual elements together based on Gestalt principles. Using this analysis, we characterize the VIF design space by a taxonomy of 12 different design patterns. Exploring in a real-world infographic dataset, we discuss the design space and potentials of VIF in light of this taxonomy.

Many applications, such as autonomous driving, heavily rely on multi-modal data where spatial alignment between the modalities is required. Most multi-modal registration methods struggle computing the spatial correspondence between the images using prevalent cross-modality similarity measures. In this work, we bypass the difficulties of developing cross-modality similarity measures, by training an image-to-image translation network on the two input modalities. This learned translation allows training the registration network using simple and reliable mono-modality metrics. We perform multi-modal registration using two networks - a spatial transformation network and a translation network. We show that by encouraging our translation network to be geometry preserving, we manage to train an accurate spatial transformation network. Compared to state-of-the-art multi-modal methods our presented method is unsupervised, requiring no pairs of aligned modalities for training, and can be adapted to any pair of modalities. We evaluate our method quantitatively and qualitatively on commercial datasets, showing that it performs well on several modalities and achieves accurate alignment.

Point clouds are a popular representation for 3D shapes. However, they encode a particular sampling without accounting for shape priors or non-local information. We advocate for the use of a hierarchical Gaussian mixture model (hGMM), which is a compact, adaptive and lightweight representation that probabilistically defines the underlying 3D surface. We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class, and also coincide with the input point cloud. PointGMM is trained over a collection of shapes to learn a class-specific prior. The hierarchical representation has two main advantages: (i) coarse-to-fine learning, which avoids converging to poor local-minima; and (ii) (an unsupervised) consistent partitioning of the input shape. We show that as a generative model, PointGMM learns a meaningful latent space which enables generating consistent interpolations between existing shapes, as well as synthesizing novel shapes. We also present a novel framework for rigid registration using PointGMM, that learns to disentangle orientation from structure of an input shape.

Existing augmented reality (AR) applications often ignore the occlusion between real hands and virtual objects when incorporating virtual objects in user's views. The challenges come from the lack of accurate depth and mismatch between real and virtual depth. This paper presents GrabAR1, a new approach that directly predicts the real-and-virtual occlusion and bypasses the depth acquisition and inference. Our goal is to enhance AR applications with interactions between hand (real) and grabbable objects (virtual). With paired images of hand and object as inputs, we formulate a compact deep neural network that learns to generate the occlusion mask. To train the network, we compile a large dataset, including synthetic data and real data. We then embed the trained network in a prototyping AR system to support real-time grabbing of virtual objects. Further, we demonstrate the performance of our method on various virtual objects, compare our method with others through two user studies, and showcase a rich variety of interaction scenarios, in which we can use bare hand to grab virtual objects and directly manipulate them.

Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing between the images. This was made possible by introducing clever regularizers to overcome the under-constrained nature of the unpaired translation problem. In this work, we introduce a novel architecture for unpaired image translation, and explore several new regularizes enabled by it. Specifically, our architecture comprises a pair of GANs, as well as a pair of translators between their respective latent spaces. These cross-translators enable us to impose several regularizing constraints on the learnt image translation operator, collectively referred to as latent cross-consistency. Our results show that our proposed architecture and latent cross-consistency constraints are able to outperform the existing state-of-the-art on a variety of image translation tasks.

Abstract In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set and maintain a well‐paced visual transition from one to the next. In this paper, we propose a conditional generative adversarial network (GAN) morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid‐based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self‐supervision, our network learns to generate visually pleasing morphing effects featuring believable in‐betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.

Visualizing high-dimensional data on a 2D canvas is generally challenging. It becomes significantly more difficult when multiple time-steps are to be presented, as the visual clutter quickly increases. Moreover, the challenge to perceive the significant temporal evolution is even greater. In this paper, we present a method to plot temporal high-dimensional data in a static scatterplot; it uses the established PCA technique to project data from multiple time-steps. The key idea is to extend each individual displacement prior to applying PCA, so as to skew the projection process, and to set a projection plane that balances the directions of temporal change and spatial variance. We present numerous examples and various visual cues to highlight the data trajectories, and demonstrate the effectiveness of the method for visualizing temporal data.

In this paper, we present a novel non-parametric clustering technique. Our technique is based on the notion that each latent cluster is comprised of layers that surround its core, where the external layers, or border points, implicitly separate the clusters. Unlike previous techniques, such as DBSCAN, where the cores of the clusters are defined directly by their densities, here the latent cores are revealed by a progressive peeling of the border points. Analyzing the density of the local neighborhoods allows identifying the border points and associating them with points of inner layers. We show that the peeling process adapts to the local densities and characteristics to successfully separate adjacent clusters (of possibly different densities). We extensively tested our technique on large sets of labeled data, including high-dimensional datasets of deep features that were trained by a convolutional neural network. We show that our technique is competitive to other state-of-the-art non-parametric methods using a fixed set of parameters throughout the experiments.

We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without requiring any explicit pairing between the motions in the training set. We leverage the fact that different homeomorphic skeletons may be reduced to a common primal skeleton by a sequence of edge merging operations, which we refer to as skeletal pooling. Thus, our main technical contribution is the introduction of novel differentiable convolution, pooling, and unpooling operators. These operators are skeleton-aware , meaning that they explicitly account for the skeleton's hierarchical structure and joint adjacency, and together they serve to transform the original motion into a collection of deep temporal features associated with the joints of the primal skeleton. In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons. Thus, retargeting can be achieved simply by encoding to, and decoding from this latent space. Our experiments show the effectiveness of our framework for motion retargeting, as well as motion processing in general, compared to existing approaches. Our approach is also quantitatively evaluated on a synthetic dataset that contains pairs of motions applied to different skeletons. To the best of our knowledge, our method is the first to perform retargeting between skeletons with differently sampled kinematic chains, without any paired examples.

Transferring the motion style from one animation clip to another, while preserving the motion content of the latter, has been a long-standing problem in character animation. Most existing data-driven approaches are supervised and rely on paired data, where motions with the same content are performed in different styles. In addition, these approaches are limited to transfer of styles that were seen during training. In this paper, we present a novel data-driven framework for motion style transfer, which learns from an unpaired collection of motions with style labels, and enables transferring motion styles not observed during training. Furthermore, our framework is able to extract motion styles directly from videos, bypassing 3D reconstruction, and apply them to the 3D input motion. Our style transfer network encodes motions into two latent codes, for content and for style, each of which plays a different role in the decoding (synthesis) process. While the content code is decoded into the output motion by several temporal convolutional layers, the style code modifies deep features via temporally invariant adaptive instance normalization (AdaIN). Moreover, while the content code is encoded from 3D joint rotations, we learn a common embedding for style from either 3D or 2D joint positions, enabling style extraction from videos. Our results are comparable to the state-of-the-art, despite not requiring paired training data, and outperform other methods when transferring previously unseen styles. To our knowledge, we are the first to demonstrate style transfer directly from videos to 3D animations - an ability which enables one to extend the set of style examples far beyond motions captured by MoCap systems.

The paradigm of image-to-image translation is leveraged for the benefit of sketch stylization via transfer of geometric textural details. Lacking the necessary volumes of data for standard training of translation systems, we advocate for operation at the patch level, where a handful of stylized sketches provide ample mining potential for patches featuring basic geometric primitives. Operating at the patch level necessitates special consideration of full sketch translation, as individual translation of patches with no regard to neighbors is likely to produce visible seams and artifacts at patch borders. Aligned pairs of styled and plain primitives are combined to form input hybrids containing styled elements around the border and plain elements within, and given as input to a seamless translation (ST) generator, whose output patches are expected to reconstruct the fully styled patch. An adversarial addition promotes generalization and robustness to diverse geometries at inference time, forming a simple and effective system for arbitrary sketch stylization, as demonstrated upon a variety of styles and sketches.

In this paper, we introduce Point2Mesh , a technique for reconstructing a surface mesh from an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape properties, the prior is defined automatically using the input point cloud, which we refer to as a self-prior. The self-prior encapsulates reoccurring geometric repetitions from a single shape within the weights of a deep neural network. We optimize the network weights to deform an initial mesh to shrink-wrap a single input point cloud. This explicitly considers the entire reconstructed shape, since shared local kernels are calculated to fit the overall object. The convolutional kernels are optimized globally across the entire shape, which inherently encourages local-scale geometric self-similarity across the shape surface. We show that shrink-wrapping a point cloud with a self-prior converges to a desirable solution; compared to a prescribed smoothness prior, which often becomes trapped in undesirable local minima. While the performance of traditional reconstruction approaches degrades in non-ideal conditions that are often present in real world scanning, i.e. , unoriented normals, noise and missing (low density) parts, Point2Mesh is robust to non-ideal conditions. We demonstrate the performance of Point2Mesh on a large variety of shapes with varying complexity.

Recently, deep generative adversarial networks for image generation have advanced rapidly; yet, only a small amount of research has focused on generative models for irregular structures, particularly meshes. Nonetheless, mesh generation and synthesis remains a fundamental topic in computer graphics. In this work, we propose a novel framework for synthesizing geometric textures. It learns geometric texture statistics from local neighborhoods ( i.e. , local triangular patches) of a single reference 3D model. It learns deep features on the faces of the input triangulation, which is used to subdivide and generate offsets across multiple scales, without parameterization of the reference or target mesh. Our network displaces mesh vertices in any direction ( i.e. , in the normal and tangential direction), enabling synthesis of geometric textures, which cannot be expressed by a simple 2D displacement map. Learning and synthesizing on local geometric patches enables a genus-oblivious framework, facilitating texture transfer between shapes of different genus.

This article presents a novel approach to learn and detect distinctive regions on 3D shapes. Unlike previous works, which require labeled data, our method is unsupervised. We conduct the analysis on point sets sampled from 3D shapes, then formulate and train a deep neural network for an unsupervised shape clustering task to learn local and global features for distinguishing shapes with respect to a given shape set. To drive the network to learn in an unsupervised manner, we design a clustering-based nonparametric softmax classifier with an iterative re-clustering of shapes, and an adapted contrastive loss for enhancing the feature embedding quality and stabilizing the learning process. By then, we encourage the network to learn the point distinctiveness on the input shapes. We extensively evaluate various aspects of our approach and present its applications for distinctiveness-guided shape retrieval, sampling, and view selection in 3D scenes.

Capturing the 3D geometry of transparent objects is a challenging task, ill-suited for general-purpose scanning and reconstruction techniques, since these cannot handle specular light transport phenomena. Existing state-of-the-art methods, designed specifically for this task, either involve a complex setup to reconstruct complete refractive ray paths, or leverage a data-driven approach based on synthetic training data. In either case, the reconstructed 3D models suffer from over-smoothing and loss of fine detail. This paper introduces a novel, high precision, 3D acquisition and reconstruction method for solid transparent objects. Using a static background with a coded pattern, we establish a mapping between the camera view rays and locations on the background. Differentiable tracing of refractive ray paths is then used to directly optimize a 3D mesh approximation of the object, while simultaneously ensuring silhouette consistency and smoothness. Extensive experiments and comparisons demonstrate the superior accuracy of our method.

Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis process. Current methods, however, require extensive supervision and training, or instead, noticeably compromise quality. In this paper, we present a method that learns how to represent data in a disentangled way, with minimal supervision, manifested solely using available pre-trained networks. Our key insight is to decouple the processes of disentanglement and synthesis, by employing a leading pre-trained unconditional image generator, such as StyleGAN. By learning to map into its latent space, we leverage both its state-of-the-art quality, and its rich and expressive latent space, without the burden of training it. We demonstrate our approach on the complex and high dimensional domain of human heads. We evaluate our method qualitatively and quantitatively, and exhibit its success with de-identification operations and with temporal identity coherency in image sequences. Through extensive experimentation, we show that our method successfully disentangles identity from other facial attributes, surpassing existing methods, even though they require more training and supervision.

The emergence of deep generative models has recently enabled the automatic generation of massive amounts of graphical content, both in 2D and in 3D. Generative Adversarial Networks (GANs) and style control mechanisms, such as Adaptive Instance Normalization (AdaIN), have proved particularly effective in this context, culminating in the state-of-the-art StyleGAN architecture. While such models are able to learn diverse distributions, provided a sufficiently large training set, they are not well-suited for scenarios where the distribution of the training data exhibits a multi-modal behavior. In such cases, reshaping a uniform or normal distribution over the latent space into a complex multi-modal distribution in the data domain is challenging, and the generator might fail to sample the target distribution well. Furthermore, existing unsupervised generative models are not able to control the mode of the generated samples independently of the other visual attributes, despite the fact that they are typically disentangled in the training data. In this paper, we introduce uMM-GAN, a novel architecture designed to better model multi-modal distributions, in an unsupervised fashion. Building upon the StyleGAN architecture, our network learns multiple modes, in a completely unsupervised manner , and combines them using a set of learned weights. We demonstrate that this approach is capable of effectively approximating a complex distribution as a superposition of multiple simple ones. We further show that uMM-GAN effectively disentangles between modes and style, thereby providing an independent degree of control over the generated content.

This work proposes Winglets, an enhancement to the classic scatterplot to better perceptually pronounce multiple classes by improving the perception of association and uncertainty of points to their related cluster. Designed as a pair of dual-sided strokes belonging to a data point, Winglets leverage the Gestalt principle of Closure to shape the perception of the form of the clusters, rather than use an explicit divisive encoding. Through a subtle design of two dominant attributes, length and orientation, Winglets enable viewers to perform a mental completion of the clusters. A controlled user study was conducted to examine the efficiency of Winglets in perceiving the cluster association and the uncertainty of certain points. The results show Winglets form a more prominent association of points into clusters and improve the perception of associating uncertainty.

In image-to-image translation the goal is to learn a mapping from one image domain to another. In the case of supervised approaches the mapping is learned from paired samples. However, collecting large sets of image pairs is often either prohibitively expensive or not possible. As a result, in recent years more attention has been given to techniques that learn the mapping from unpaired sets. In our work, we show that injecting implicit pairs into unpaired sets strengthens the mapping between the two domains, improves the compatibility of their distributions, and leads to performance boosting of unsupervised techniques by up to 12% across several measurements. The competence of the implicit pairs is further displayed with the use of pseudo-pairs, i.e., paired samples which only approximate a real pair. We demonstrate the effect of the approximated implicit samples on image-to-image translation problems, where such pseudo-pairs may be synthesized in one direction, but not in the other. We further show that pseudo-pairs are significantly more effective as implicit pairs in an unpaired setting, than directly using them explicitly in a paired setting.

Many images shared over the web include overlaid objects, or visual motifs, such as text, symbols or drawings, which add a description or decoration to the image. For example, decorative text that specifies where the image was taken, repeatedly appears across a variety of different images. Often, the reoccurring visual motif, is semantically similar, yet, differs in location, style and content (e.g. text placement, font and letters). This work proposes a deep learning based technique for blind removal of such objects. In the blind setting, the location and exact geometry of the motif are unknown. Our approach simultaneously estimates which pixels contain the visual motif, and synthesizes the underlying latent image. It is applied to a single input image, without any user assistance in specifying the location of the motif, achieving state-of-the-art results for blind removal of both opaque and semi-transparent visual motifs.

Multi-scale context information has proven to be essential for object segmentation tasks. Recent works construct the multi-scale context by aggregating convolutional feature maps extracted by different levels of a deep neural network. This is typically done by propagating and fusing features in a one-directional, top-down and bottom-up, manner. In this work, we introduce ZigZagNet, which aggregates a richer multi-context feature map by using not only dense top-down and bottom-up propagation, but also by introducing pathways crossing between different levels of the top-down and the bottom-up hierarchies, in a zig-zag fashion. Furthermore, the context information is exchanged and aggregated over multiple stages, where the fused feature maps from one stage are fed into the next one, yielding a more comprehensive context for improved segmentation performance. Our extensive evaluation on the public benchmarks demonstrates that ZigZagNet surpasses the state-of-the-art accuracy for both semantic segmentation and instance segmentation tasks.

We present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-the-art learning-based and optimazation-based approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details.

Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN1, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces. To realize a working GAN network, we construct an up-down-up expansion unit in the generator for upsampling point features with error feedback and self-correction, and formulate a self-attention unit to enhance the feature integration. Further, we design a compound loss with adversarial, uniform and reconstruction terms, to encourage the discriminator to learn more latent patterns and enhance the output point distribution uniformity. Qualitative and quantitative evaluations demonstrate the quality of our results over the state-of-the-arts in terms of distribution uniformity, proximity-to-surface, and 3D reconstruction quality.

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather than only from a distribution confined to the training data. In other words, we would like the generative model to go beyond the observed samples and learn to generate ``unseen'', yet still plausible, data. In our work, we present CompoNet, a generative neural network for 2D or 3D shapes that is based on a part-based prior, where the key idea is for the network to synthesize shapes by varying both the shape parts and their compositions. Treating a shape not as an unstructured whole, but as a (re-)composable set of deformable parts, adds a combinatorial dimension to the generative process to enrich the diversity of the output, encouraging the generator to venture more into the ``unseen''. We show that our part-based model generates richer variety of plausible shapes compared with baseline generative models. To this end, we introduce two quantitative metrics to evaluate the diversity of a generative model and assess how well the generated data covers both the training data and unseen data from the same target distribution.

Abstract We present a new video‐based performance cloning technique. After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances. All of the training data and the driving performances are provided as ordinary video segments, without motion capture or depth information. Our generative model is realized as a deep neural network with two branches, both of which train the same space‐time conditional generator, using shared weights. One branch, responsible for learning to generate the appearance of the target actor in various poses, uses paired training data, self‐generated from the reference video. The second branch uses unpaired data to improve generation of temporally coherent video renditions of unseen pose sequences. Through data augmentation, our network is able to synthesize images of the target actor in poses never captured by the reference video. We demonstrate a variety of promising results, where our method is able to generate temporally coherent videos, for challenging scenarios where the reference and driving videos consist of very different dance performances.

Abstract We present a method for determining which facial parts (mouth, nose, etc.) best characterize an individual, given a set of that individual's portraits. We introduce a novel distinctiveness analysis of a set of portraits, which leverages the deep features extracted by a pre‐trained face recognition CNN and a hair segmentation FCN, in the context of a weakly supervised metric learning scheme. Our analysis enables the generation of a polarized class activation map (PCAM) for an individual's portrait via a transformation that localizes and amplifies the discriminative regions of the deep feature maps extracted by the aforementioned networks. A user study that we conducted shows that there is a surprisingly good agreement between the face parts that users indicate as characteristic and the face parts automatically selected by our method. We demonstrate a few applications of our method, including determining the most and the least representative portraits among a set of portraits of an individual, and the creation of facial hybrids: portraits that combine the characteristic recognizable facial features of two individuals. Our face characterization analysis is also effective for ranking portraits in order to find an individual's look‐alikes (Doppelgängers).

A metric for natural image patches is an important tool for analyzing images. An efficient means of learning one is to train a deep network to map an image patch to a vector space, in which the Euclidean distance reflects patch similarity. Previous attempts learned such an embedding in a supervised manner, requiring the availability of many annotated images. In this paper, we present an unsupervised embedding of natural image patches, avoiding the need for annotated images. The key idea is that the similarity of two patches can be learned from the prevalence of their spatial proximity in natural images. Clearly, relying on this simple principle, many spatially nearby pairs are outliers. However, as we show, these outliers do not harm the convergence of the metric learning. We show that our unsupervised embedding approach is more effective than a supervised one or one that uses deep patch representations. Moreover, we show that it naturally lends itself to an efficient self-supervised domain adaptation technique onto a target domain that contains a common foreground object.

Multi-dimensional scaling (MDS) plays a central role in data-exploration, dimensionality reduction and visualization. State-of-the-art MDS algorithms are not robust to outliers, yielding significant errors in the embedding even when only a handful of outliers are present. In this paper, we introduce a technique to detect and filter outliers based on geometric reasoning. We test the validity of triangles formed by three points, and mark a triangle as broken if its triangle inequality does not hold. The premise of our work is that unlike inliers, outlier distances tend to break many triangles. Our method is tested and its performance is evaluated on various datasets and distributions of outliers. We demonstrate that for a reasonable amount of outliers, e.g., under 20 percent, our method is effective, and leads to a high embedding quality.

Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to another. While humans move in three dimensions, the vast majority of human motions are captured using video, requiring 2D-to-3D pose and camera recovery, before existing retargeting approaches may be applied. In this paper, we present a new method for retargeting video-captured motion between different human performers, without the need to explicitly reconstruct 3D poses and/or camera parameters. In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view. Our key idea is to train a deep neural network to decompose temporal sequences of 2D poses into three components: motion, skeleton, and camera view-angle. Having extracted such a representation, we are able to re-combine motion with novel skeletons and camera views, and decode a retargeted temporal sequence, which we compare to a ground truth from a synthetic dataset. We demonstrate that our framework can be used to robustly extract human motion from videos, bypassing 3D reconstruction, and outperforming existing retargeting methods, when applied to videos in-the-wild. It also enables additional applications, such as performance cloning, video-driven cartoons, and motion retrieval.

The process of aligning a pair of shapes is a fundamental operation in computer graphics. Traditional approaches rely heavily on matching corresponding points or features to guide the alignment, a paradigm that falters when significant shape portions are missing. These techniques generally do not incorporate prior knowledge about expected shape characteristics, which can help compensate for any misleading cues left by inaccuracies exhibited in the input shapes. We present an approach based on a deep neural network, leveraging shape datasets to learn a shape-aware prior for source-to-target alignment that is robust to shape incompleteness. In the absence of ground truth alignments for supervision, we train a network on the task of shape alignment using incomplete shapes generated from full shapes for self-supervision. Our network, called ALIGNet , is trained to warp complete source shapes to incomplete targets, as if the target shapes were complete, thus essentially rendering the alignment partial-shape agnostic . We aim for the network to develop specialized expertise over the common characteristics of the shapes in each dataset, thereby achieving a higher-level understanding of the expected shape space to which a local approach would be oblivious. We constrain ALIGNet through an anisotropic total variation identity regularization to promote piecewise smooth deformation fields, facilitating both partial-shape agnosticism and post-deformation applications. We demonstrate that ALIGNet learns to align geometrically distinct shapes and is able to infer plausible mappings even when the target shape is significantly incomplete. We show that our network learns the common expected characteristics of shape collections without over-fitting or memorization, enabling it to produce plausible deformations on unseen data during test time.

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly captureboth shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN , a convolutional neural network designed specifically for triangular meshes. Analogous to classic CNNs, MeshCNN combines specialized convolution and pooling layers that operate on the mesh edges, by leveraging their intrinsic geodesic connections. Convolutions are applied on edges and the four edges of their incident triangles, and pooling is applied via an edge collapse operation that retains surface topology, thereby, generating new mesh connectivity for the subsequent convolutions. MeshCNN learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones. We demonstrate the effectiveness of MeshCNN on various learning tasks applied to 3D meshes.

We present a generative neural network that enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently. Our key observation is that indoor scene structures are inherently hierarchical . Hence, our network is not convolutional; it is a recursive neural network, or RvNN. Using a dataset of annotated scene hierarchies, we train a variational recursive autoencoder , or RvNN-VAE, which performs scene object grouping during its encoding phase and scene generation during decoding. Specifically, a set of encoders are recursively applied to group 3D objects based on support, surround, and co-occurrence relations in a scene, encoding information about objects’ spatial properties, semantics , and relative positioning with respect to other objects in the hierarchy. By training a variational autoencoder (VAE), the resulting fixed-length codes roughly follow a Gaussian distribution. A novel 3D scene can be generated hierarchically by the decoder from a randomly sampled code from the learned distribution. We coin our method GRAINS, for Generative Recursive Autoencoders for INdoor Scenes. We demonstrate the capability of GRAINS to generate plausible and diverse 3D indoor scenes and compare with existing methods for 3D scene synthesis. We show applications of GRAINS including 3D scene modeling from 2D layouts, scene editing, and semantic scene segmentation via PointNet whose performance is boosted by the large quantity and variety of 3D scenes generated by our method.

We present SAGNet, a structure-aware generative model for 3D shapes. Given a set of segmented objects of a certain class, the geometry of their parts and the pairwise relationships between them (the structure) are jointly learned and embedded in a latent space by an autoencoder. The encoder intertwines the geometry and structure features into a single latent code, while the decoder disentangles the features and reconstructs the geometry and structure of the 3D model. Our autoencoder consists of two branches, one for the structure and one for the geometry. The key idea is that during the analysis, the two branches exchange information between them, thereby learning the dependencies between structure and geometry and encoding two augmented features, which are then fused into a single latent code. This explicit intertwining of information enables separately controlling the geometry and the structure of the generated models. We evaluate the performance of our method and conduct an ablation study. We explicitly show that encoding of shapes accounts for both similarities in structure and geometry. A variety of quality results generated by SAGNet are presented.

We introduce LOGAN, a deep neural network aimed at learning generalpurpose shape transforms from unpaired domains. The network is trained on two sets of shapes, e.g., tables and chairs, while there is neither a pairing between shapes from the domains as supervision nor any point-wise correspondence between any shapes. Once trained, LOGAN takes a shape from one domain and transforms it into the other. Our network consists of an autoencoder to encode shapes from the two input domains into a common latent space , where the latent codes concatenate multi-scale shape features, resulting in an overcomplete representation. The translator is based on a generative adversarial network (GAN), operating in the latent space, where an adversarial loss enforces cross-domain translation while a feature preservation loss ensures that the right shape features are preserved for a natural shape transform. We conduct ablation studies to validate each of our key network designs and demonstrate superior capabilities in unpaired shape transforms on a variety of examples over baselines and state-of-the-art approaches. We show that LOGAN is able to learn what shape features to preserve during shape translation, either local or non-local, whether content or style, depending solely on the input domains for training.

We introduce a data-driven method to generate a large number of plausible, closely interacting 3D human pose-pairs, for a given motion category, e.g., wrestling or salsa dance. With much difficulty in acquiring close interactions using 3D sensors, our approach utilizes abundant existing video data which cover many human activities. Instead of treating the data generation problem as one of reconstruction, either through 3D acquisition or direct 2D-to-3D data lifting from video annotations, we present a solution based on Markov Chain Monte Carlo (MCMC) sampling. Given a motion category and a set of video frames depicting the motion with the 2D pose-pair in each frame annotated, we start the sampling with one or few seed 3D pose-pairs which are manually created based on the target motion category. The initial set is then augmented by MCMC sampling around the seeds, via the Metropolis-Hastings algorithm and guided by a probability density function (PDF) that is defined by two terms to bias the sampling towards 3D pose-pairs that are physically valid and plausible for the motion category. With a focus on efficient sampling over the space of close interactions, rather than pose spaces, we develop a novel representation called interaction coordinates (IC) to encode both poses and their interactions in an integrated manner. Plausibility of a 3D pose-pair is then defined based on the IC and with respect to the annotated 2D pose-pairs from video. We show that our sampling-based approach is able to efficiently synthesize a large volume of plausible, closely interacting 3D pose-pairs which provide a good coverage of the input 2D pose-pairs.

Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space. The expanded feature is then split to a multitude of features, which are then reconstructed to an upsampled point set. Our network is applied at a patch-level, with a joint loss function that encourages the upsampled points to remain on the underlying surface with a uniform distribution. We conduct various experiments using synthesis and scan data to evaluate our method and demonstrate its superiority over some baseline methods and an optimization-based method. Results show that our upsampled points have better uniformity and are located closer to the underlying surfaces.

Conventional deep learning classifiers are static in the sense that they are trained on a predefined set of classes and learning to classify a novel class typically requires re-training. In this work, we address the problem of Low-Shot network-expansion learning. We introduce a learning framework which enables expanding a pre-trained (base) deep network to classify novel classes when the number of examples for the novel classes is particularly small. We present a simple yet powerful hard distillation method where the base network is augmented with additional weights to classify the novel classes, while keeping the weights of the base network unchanged. We show that since only a small number of weights needs to be trained, the hard distillation excels in low-shot training scenarios. Furthermore, hard distillation avoids detriment to classification performance on the base classes. Finally, we show that low-shot network expansion can be done with a very small memory footprint by using a compact generative model of the base classes training data with only a negligible degradation relative to learning with the full training set.

In this paper, we introduce an online video-based system that actively assists users in assembly tasks. The system guides and monitors the assembly process by providing instructions and feedback on possibly erroneous operations, enabling easy and effective guidance in AR/MR applications. The core of our system is an online video-based assembly parsing method that can understand the assembly process, which is known to be extremely hard previously. Our method exploits the availability of the participating parts to significantly alleviate the problem, reducing the recognition task to an identification problem, within a constrained search space. To further constrain the search space, and understand the observed assembly activity, we introduce a tree-based global-inference technique. Our key idea is to incorporate part-interaction rules as powerful constraints which significantly regularize the search space and correctly parse the assembly video at interactive rates. Complex examples demonstrate the effectiveness of our method.

Abstract Motion capture sequences may contain erroneous data, especially when the motion is complex or performers are interacting closely and occlusions are frequent. Common practice is to have specialists visually detect the abnormalities and fix them manually. In this paper, we present a method to automatically analyze and fix motion capture sequences by using self‐similarity analysis. The premise of this work is that human motion data has a high‐degree of self‐similarity. Therefore, given enough motion data, erroneous motions are distinct when compared to other motions. We utilizemotion‐wordsthat consist of short sequences of transformations of groups of joints around a given motion frame. We search for the K‐nearest neighbors (KNN) set of each word using dynamic time warping and use it to detect and fix erroneous motions automatically. We demonstrate the effectiveness of our method in various examples, and evaluate by comparing to alternative methods and to manual cleaning.

Abstract We present an interactive method that allows users to easily abstract complex 3D models with only a few strokes. The key idea is to employ well‐known Gestalt principles to help generalizing user inputs into a full model abstraction while accounting for form, perceptual patterns and semantics of the model. Using these principles, we alleviate the user's need to explicitly define shape abstractions. We utilize structural characteristics such as repetitions, regularity and similarity to transform user strokes into full 3D abstractions. As the user sketches over shape elements, we identify Gestalt groups and later abstract them to maintain their structural meaning. Unlike previous approaches, we operate directly on the geometric elements, in a sense applying Gestalt principles in 3D. We demonstrate the effectiveness of our approach with a series of experiments, including a variety of complex models and two extensive user studies to evaluate our framework.

Abstract In this paper we introduce a video post-processing method that enhances the rhythm of a dancing performance, in the sense that the dancing movements are more in time to the beat of the music. The dancing performance as observed in a video is analyzed and segmented into motion intervals delimited by motion beats. We present an image-space method to extract the motion beats of a video by detecting frames at which there is a significant change in direction or motion stops. The motion beats are then synchronized with the music beats such that as many beats as possible are matched with as little as possible time-warping distortion to the video. We show two applications for this cross-media synchronization: one where a given dance performance is enhanced to be better synchronized with its original music, and one where a given dance video is automatically adapted to be synchronized with different music.

We present a structure-aware technique to consolidate noisy data, which we use as a pre-process for standard clustering and dimensionality reduction. Our technique is related to mean shift, but instead of seeking density modes, it reveals and consolidates continuous high density structures such as curves and surface sheets in the underlying data while ignoring noise and outliers. We provide a theoretical analysis under a Gaussian noise model, and show that our approach significantly improves the performance of many non-linear dimensionality reduction and clustering algorithms in challenging scenarios.

Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications. This paper presents a novel method for sparse cross-domain correspondence. Our method is designed for pairs of images where the main objects of interest may belong to different semantic categories and differ drastically in shape and appearance, yet still contain semantically related or geometrically similar parts. Our approach operates on hierarchies of deep features, extracted from the input images by a pre-trained CNN. Specifically, starting from the coarsest layer in both hierarchies, we search for Neural Best Buddies (NBB): pairs of neurons that are mutual nearest neighbors. The key idea is then to percolate NBBs through the hierarchy, while narrowing down the search regions at each level and retaining only NBBs with significant activations. Furthermore, in order to overcome differences in appearance, each pair of search regions is transformed into a common appearance. We evaluate our method via a user study, in addition to comparisons with alternative correspondence approaches. The usefulness of our method is demonstrated using a variety of graphics applications, including cross-domain image alignment, creation of hybrid images, automatic image morphing, and more.

Many analysis tasks for human motion rely on high-level similarity between sequences of motions, that are not an exact matches in joint angles, timing, or ordering of actions. Even the same movements performed by the same person can vary in duration and speed. Similar motions are characterized by similar sets of actions that appear frequently. In this paper we introduce motion motifs and motion signatures that are a succinct but descriptive representation of motion sequences. We first break the motion sequences to short-term movements called motion words, and then cluster the words in a high-dimensional feature space to find motifs. Hence, motifs are words that are both common and descriptive, and their distribution represents the motion sequence. To cluster words and find motifs, the challenge is to define an effective feature space, where the distances among motion words are semantically meaningful, and where variations in speed and duration are handled. To this end, we use a deep neural network to embed the motion words into feature space using a triplet loss function. To define a signature, we choose a finite set of motion-motifs, creating a bag-of-motifs representation for the sequence. Motion signatures are agnostic to movement order, speed or duration variations, and can distinguish fine-grained differences between motions of the same class. We illustrate examples of characterizing motion sequences by motifs, and for the use of motion signatures in a number of applications.

We introduce a computational solution for cost-efficient 3D fabrication using universal building blocks. Our key idea is to employ a set of universal blocks, which can be massively prefabricated at a low cost, to quickly assemble and constitute a significant internal core of the target object, so that only the residual volume need to be 3D printed online. We further improve the fabrication efficiency by decomposing the residual volume into a small number of printing-friendly pyramidal pieces. Computationally, we face a coupled decomposition problem: decomposing the input object into an internal core and residual, and decomposing the residual, to fulfill a combination of objectives for efficient 3D fabrication. To this end, we formulate an optimization that jointly minimizes the residual volume, the number of pyramidal residual pieces, and the amount of support waste when printing the residual pieces. To solve the optimization in a tractable manner, we start with a maximal internal core and iteratively refine it with local cuts to minimize the cost function. Moreover, to efficiently explore the large search space, we resort to cost estimates aided by pre-computation and avoid the need to explicitly construct pyramidal decompositions for each solution candidate. Results show that our method can iteratively reduce the estimated printing time and cost, as well as the support waste, and helps to save hours of fabrication time and much material consumption.

We introduce a learning-based method to reconstruct objects acquired in a casual handheld scanning setting with a depth camera. Our method is based on two core components. First, a deep network that provides a semantic segmentation and labeling of the frames of an input RGBD sequence. Second, an alignment and reconstruction method that employs the semantic labeling to reconstruct the acquired object from the frames. We demonstrate that the use of a semantic labeling improves the reconstructions of the objects, when compared to methods that use only the depth information of the frames. Moreover, since training a deep network requires a large amount of labeled data, a key contribution of our work is an active self-learning framework to simplify the creation of the training data. Specifically, we iteratively predict the labeling of frames with the neural network, reconstruct the object from the labeled frames, and evaluate the confidence of the labeling, to incrementally train the neural network while requiring only a small amount of user-provided annotations. We show that this method enables the creation of data for training a neural network with high accuracy, while requiring only little manual effort.

Endowing 3D objects with realistic surface appearance is a challenging and time-demanding task, as real-world surfaces typically exhibit a plethora of spatially variant geometric and photometric detail. Not surprisingly, computer artists commonly use images of real-world objects as an inspiration and a reference for their digital creations. However, despite two decades of research on image-based modeling, there are still no tools available for automatically extracting the detailed appearance (microgeometry and texture) of a 3D surface from a single image. In this article, we present a novel user-assisted approach for quickly and easily extracting a nonparametric appearance model from a single photograph of a reference object. The extraction process requires a user-provided proxy, whose geometry roughly approximates that of the object in the image. Since the proxy is just a rough approximation, it is necessary to align and deform it so as to match the reference object. The main contribution of this work is a novel technique to perform such an alignment, which enables accurate joint recovery of geometric detail and reflectance. The correlations between the recovered geometry at various scales and the spatially varying reflectance constitute a nonparametric appearance model. Once extracted, the appearance model may then be applied to various 3D shapes, whose large-scale geometry may differ considerably from that of the original reference object. Thus, our approach makes it possible to construct an appearance library, allowing users to easily enrich detail-less 3D shapes with realistic geometric detail and surface texture.

We introduce a generative model for 3D man-made shapes. The presented method takes a global-to-local (G2L) approach. An adversarial network (GAN) is built first to construct the overall structure of the shape, segmented and labeled into parts. A novel conditional auto-encoder (AE) is then augmented to act as a part-level refiner. The GAN, associated with additional local discriminators and quality losses, synthesizes a voxel-based model, and assigns the voxels with part labels that are represented in separate channels. The AE is trained to amend the initial synthesis of the parts, yielding more plausible part geometries. We also introduce new means to measure and evaluate the performance of an adversarial generative model. We demonstrate that our global-to-local generative model produces significantly better results than a plain three-dimensional GAN, in terms of both their shape variety and the distribution with respect to the training data.

Capturing aerial videos with a quadrotor-mounted camera is a challenging creative task, as it requires the simultaneous control of the quadrotor's motion and the mounted camera's orientation. Letting the drone follow a pre-planned trajectory is a much more appealing option, and recent research has proposed a number of tools designed to automate the generation of feasible camera motion plans; however, these tools typically require the user to specify and edit the camera path, for example by providing a complete and ordered sequence of key viewpoints. In this paper, we propose a higher level tool designed to enable even novice users to easily capture compelling aerial videos of large-scale outdoor scenes. Using a coarse 2.5D model of a scene, the user is only expected to specify starting and ending viewpoints and designate a set of landmarks, with or without a particular order. Our system automatically generates a diverse set of candidate local camera moves for observing each landmark, which are collision-free, smooth, and adapted to the shape of the landmark. These moves are guided by a landmark-centric view quality field, which combines visual interest and frame composition. An optimal global camera trajectory is then constructed that chains together a sequence of local camera moves, by choosing one move for each landmark and connecting them with suitable transition trajectories. This task is formulated and solved as an instance of the Set Traveling Salesman Problem.

We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The architecture of the P2P-NET is that of a bi-directional point displacement network, which transforms a source point set to a prediction of the target point set with the same cardinality, and vice versa, by applying point-wise displacement vectors learned from data. P2P-NET is trained on paired shapes from the source and target domains, but without relying on point-to-point correspondences between the source and target point sets. The training loss combines two uni-directional geometric losses, each enforcing a shape-wise similarity between the predicted and the target point sets, and a cross-regularization term to encourage consistency between displacement vectors going in opposite directions. We develop and present several different applications enabled by our general-purpose bidirectional P2P-NET to highlight the effectiveness, versatility, and potential of our network in solving a variety of point-based shape transformation problems.

We present an automatic algorithm for subtractive manufacturing of freeform 3D objects using high-speed machining (HSM) via CNC. A CNC machine operates a cylindrical cutter to carve off material from a 3D shape stock, following a tool path, to "expose" the target object. Our method decomposes the input object's surface into a small number of patches each of which is fully accessible and machinable by the CNC machine, in continuous fashion, under a fixed cutter-object setup configuration. This is achieved by covering the input surface with a minimum number of accessible regions and then extracting a set of machinable patches from each accessible region. For each patch obtained, we compute a continuous, space-filling, and iso-scallop tool path which conforms to the patch boundary, enabling efficient carving with high-quality surface finishing. The tool path is generated in the form of connected Fermat spirals , which have been generalized from a 2D fill pattern for layered manufacturing to work for curved surfaces. Furthermore, we develop a novel method to control the spacing of Fermat spirals based on directional surface curvature and adapt the heat method to obtain iso-scallop carving. We demonstrate automatic generation of accessible and machinable surface decompositions and iso-scallop Fermat spiral carving paths for freeform 3D objects. Comparisons are made to tool paths generated by commercial software in terms of real machining time and surface quality.

The real world exhibits an abundance of non-stationary textures. Examples include textures with large scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle.

Understanding semantic similarity among images is the core of a wide range of computer graphics and computer vision applications. However, the visual context of images is often ambiguous as images that can be perceived with emphasis on different attributes. In this paper, we present a method for learning the semantic visual similarity among images, inferring their latent attributes and embedding them into multi-spaces corresponding to each latent attribute. We consider the multi-embedding problem as an optimization function that evaluates the embedded distances with respect to qualitative crowdsourced clusterings. The key idea of our approach is to collect and embed qualitative pairwise tuples that share the same attributes in clusters. To ensure similarity attribute sharing among multiple measures, image classification clusters are presented to, and solved by users. The collected image clusters are then converted into groups of tuples, which are fed into our group optimization algorithm that jointly infers the attribute similarity and multi-attribute embedding. Our multi-attribute embedding allows retrieving similar objects in different attribute spaces. Experimental results show that our approach outperforms state-of-the-art multi-embedding approaches on various datasets, and demonstrate the usage of the multi-attribute embedding in image retrieval application.

Fully convolutional network (FCN) has been successfully applied in semantic segmentation of scenes represented with RGB images. Images augmented with depth channel provide more understanding of the geometric information of the scene in the image. The question is how to best exploit this additional information to improve the segmentation performance. In this paper, we present a neural network with multiple branches for segmenting RGB-D images. Our approach is to use the available depth to split the image into layers with common visual characteristic of objects/scenes, or common “scene-resolution”. We introduce context-aware receptive field (CaRF) which provides a better control on the relevant contextual information of the learned features. Equipped with CaRF, each branch of the network semantically segments relevant similar scene-resolution, leading to a more focused domain which is easier to learn. Furthermore, our network is cascaded with features from one branch augmenting the features of adjacent branch. We show that such cascading of features enriches the contextual information of each branch and enhances the overall performance. The accuracy that our network achieves outperforms the state-of-the-art methods on two public datasets.

Abstract Many image editing applications rely on the analysis of image patches. In this paper, we present a method to analyze patches by embedding them to a vector space, in which the Euclidean distance reflects patch similarity. Inspired by Word2Vec, we term our approachPatch2Vec. However, there is a significant difference between words and patches. Words have a fairly small and well defined dictionary. Image patches, on the other hand, have no such dictionary and the number of different patch types is not well defined. The problem is aggravated by the fact that each patch might contain several objects and textures. Moreover, Patch2Vec should be universal because it must be able to map never‐seen‐before texture to the vector space. The mapping is learned by analyzing the distribution of all natural patches. We use Convolutional Neural Networks (CNN) to learn Patch2Vec. In particular, we train a CNN on labeled images with a triplet‐loss objective function. The trained network encodes a given patch to a 128D vector. Patch2Vec is evaluated visually, qualitatively, and quantitatively. We then use several variants of an interactive single‐click image segmentation algorithm to demonstrate the power of our method.

Autonomous reconstruction of unknown scenes by a mobile robot inherently poses the question of balancing between exploration efficacy and reconstruction quality. We present a navigation-by-reconstruction approach to address this question, where moving paths of the robot are planned to account for both global efficiency for fast exploration and local smoothness to obtain high-quality scans. An RGB-D camera, attached to the robot arm, is dictated by the desired reconstruction quality as well as the movement of the robot itself. Our key idea is to harness a time-varying tensor field to guide robot movement, and then solve for 3D camera control under the constraint of the 2D robot moving path. The tensor field is updated in real time, conforming to the progressively reconstructed scene. We show that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene. We have conducted numerous tests with a mobile robot, and demonstrate that our method leads to a smooth exploration and high-quality reconstruction of unknown indoor scenes.

The paper presents a novel three-dimensional shape acquisition and reconstruction method based on the well-known Archimedes equality between fluid displacement and the submerged volume. By repeatedly dipping a shape in liquid in different orientations and measuring its volume displacement, we generate the dip transform : a novel volumetric shape representation that characterizes the object's surface. The key feature of our method is that it employs fluid displacements as the shape sensor. Unlike optical sensors, the liquid has no line-of-sight requirements, it penetrates cavities and hidden parts of the object, as well as transparent and glossy materials, thus bypassing all visibility and optical limitations of conventional scanning devices. Our new scanning approach is implemented using a dipping robot arm and a bath of water, via which it measures the water elevation. We show results of reconstructing complex 3D shapes and evaluate the quality of the reconstruction with respect to the number of dips.

We present a technique to automatically animate a still portrait, making it possible for the subject in the photo to come to life and express various emotions. We use a driving video (of a different subject) and develop means to transfer the expressiveness of the subject in the driving video to the target portrait. In contrast to previous work that requires an input video of the target face to reenact a facial performance, our technique uses only a single target image. We animate the target image through 2D warps that imitate the facial transformations in the driving video. As warps alone do not carry the full expressiveness of the face, we add fine-scale dynamic details which are commonly associated with facial expressions such as creases and wrinkles. Furthermore, we hallucinate regions that are hidden in the input target face, most notably in the inner mouth. Our technique gives rise to reactive profiles , where people in still images can automatically interact with their viewers. We demonstrate our technique operating on numerous still portraits from the internet.

We introduce a method for co-locating style-defining elements over a set of 3D shapes. Our goal is to translate high-level style descriptions, such as “Ming” or “European” for furniture models, into explicit and localized regions over the geometric models that characterize each style. For each style, the set of style-defining elements is defined as the union of all the elements that are able to discriminate the style. Another property of the style-defining elements is that they are frequently occurring, reflecting shape characteristics that appear across multiple shapes of the same style. Given an input set of 3D shapes spanning multiple categories and styles, where the shapes are grouped according to their style labels, we perform a cross-category co-analysis of the shape set to learn and spatially locate a set of defining elements for each style. This is accomplished by first sampling a large number of candidate geometric elements and then iteratively applying feature selection to the candidates, to extract style-discriminating elements until no additional elements can be found. Thus, for each style label, we obtain sets of discriminative elements that together form the superset of defining elements for the style. We demonstrate that the co-location of style-defining elements allows us to solve problems such as style classification, and enables a variety of applications such as style-revealing view selection, style-aware sampling, and style-driven modeling for 3D shapes.

Example-based texture synthesis has been an active research problem for over two decades. Still, synthesizing textures with nonlocal structures remains a challenge. In this article, we present a texture synthesis technique that builds upon convolutional neural networks and extracted statistics of pretrained deep features. We introduce a structural energy, based on correlations among deep features, which capture the self-similarities and regularities characterizing the texture. Specifically, we show that our technique can synthesize textures that have structures of various scales, local and nonlocal, and the combination of the two.

Reconfigurable assemblies consist of a common set of parts that can be assembled into different forms for use in different situations. Designing these assemblies is a complex problem, since it requires a compatible decomposition of shapes with correspondence across forms, and a planning of well-matched joints to connect parts in each form. This paper presents computational methods as tools to assist the design and construction of reconfigurable assemblies, typically for furniture. There are three key contributions in this work. First, we present the compatible decomposition as a weakly-constrained dissection problem, and derive its solution based on a dynamic bipartite graph to construct parts across multiple forms; particularly, we optimize the parts reuse and preserve the geometric semantics. Second, we develop a joint connection graph to model the solution space of reconfigurable assemblies with part and joint compatibility across different forms. Third, we formulate the backward interlocking and multi-key interlocking models, with which we iteratively plan the joints consistently over multiple forms. We show the applicability of our approach by constructing reconfigurable furniture of various complexities, extend it with recursive connections to generate extensible and hierarchical structures, and fabricate a number of results using 3D printing, 2D laser cutting, and woodworking.

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance on the task of 2D pose estimation from a single image, by training on images with 2D annotations collected by crowd sourcing. This suggests that similar success could be achieved for direct estimation of 3D poses. However, 3D poses are much harder to annotate, and the lack of suitable annotated training images hinders attempts towards end-to-end solutions. To address this issue, we opt to automatically synthesize training images with ground truth pose annotations. Our work is a systematic study along this road. We find that pose space coverage and texture diversity are the key ingredients for the effectiveness of synthetic training data. We present a fully automatic, scalable approach that samples the human pose space for guiding the synthesis procedure and extracts clothing textures from real images. Furthermore, we explore domain adaptation for bridging the gap between our synthetic training images and real testing photos. We demonstrate that CNNs trained with our synthetic images out-perform those trained with real photos on 3D pose estimation tasks.

Abstract Smoothness is a quality that feels aesthetic and pleasing to the human eye. We present an algorithm for finding “as‐smooth‐as‐possible” sequences in image collections. In contrast to previous work, our method does not assume that the images show a common 3D scene, but instead may depict different object instances with varying deformations, and significant variation in lighting, texture, and color appearance. Our algorithm does not rely on a notion of camera pose, view direction, or 3D representation of an underlying scene, but instead directly optimizes the smoothness of the apparent motion of local point matches among the collection images. We increase the smoothness of our sequences by performing a global similarity transform alignment, as well as localized geometric wobble reduction and appearance stabilization. Our technique gives rise to a new kind of image morphing algorithm, in which the in‐between motion is derived in a data‐driven manner from a smooth sequence of real images without any user intervention. This new type of morph can go far beyond the ability of traditional techniques. We also demonstrate that our smooth sequences allow exploring large image collections in a stable manner.

Abstract Computerized route planning tools are widely used today by travelers all around the globe, while 3D terrain and urban models are becoming increasingly elaborate and abundant. This makes it feasible to generate a virtual 3D flyby along a planned route. Such a flyby may be useful, either as a preview of the trip, or as an after‐the‐fact visual summary. However, a naively generated preview is likely to contain many boring portions, while skipping too quickly over areas worthy of attention. In this paper, we introduce 3D trip synopsis: a continuous visual summary of a trip that attempts to maximize the total amount of visual interest seen by the camera. The main challenge is to generate a synopsis of a prescribed short duration, while ensuring a visually smooth camera motion. Using an application‐specific visual interest metric, we measure the visual interest at a set of viewpoints along an initial camera path, and maximize the amount of visual interest seen in the synopsis by varying the speed along the route. A new camera path is then computed using optimization to simultaneously satisfy requirements, such as smoothness, focus and distance to the route. The process is repeated until convergence. The main technical contribution of this work is a new camera control method, which iteratively adjusts the camera trajectory and determines all of the camera trajectory parameters, including the camera position, altitude, heading, and tilt. Our results demonstrate the effectiveness of our trip synopses, compared to a number of alternatives.

We address the problem of autonomously exploring unknown objects in a scene by consecutive depth acquisitions. The goal is to reconstruct the scene while online identifying the objects from among a large collection of 3D shapes. Fine-grained shape identification demands a meticulous series of observations attending to varying views and parts of the object of interest. Inspired by the recent success of attention-based models for 2D recognition, we develop a 3D Attention Model that selects the best views to scan from, as well as the most informative regions in each view to focus on, to achieve efficient object recognition. The region-level attention leads to focus-driven features which are quite robust against object occlusion. The attention model, trained with the 3D shape collection, encodes the temporal dependencies among consecutive views with deep recurrent networks. This facilitates order-aware view planning accounting for robot movement cost. In achieving instance identification, the shape collection is organized into a hierarchy, associated with pre-trained hierarchical classifiers. The effectiveness of our method is demonstrated on an autonomous robot (PR) that explores a scene and identifies the objects to construct a 3D scene model.

We present a technique to synthesize time-varying weathered textures. Given a single texture image as input, the degree of weathering at different regions of the input texture is estimated by prevalence analysis of texture patches. This information then allows to gracefully increase or decrease the popularity of weathered patches, simulating the evolution of texture appearance both backward and forward in time. Our method can be applied to a wide variety of different textures since the reaction of the material to weathering effects is physically-oblivious and learned from the input texture itself. The weathering process evolves new structures as well as color variations, providing rich and natural results. In contrast with existing methods, our method does not require any user interaction or assistance. We demonstrate our technique on various textures, and their application to time-varying weathering of 3D scenes. We also extend our method to handle multi-layered textures, weathering transfer, and interactive weathering painting.

We introduce a co-analysis technique designed for correspondence inference within large shape collections. Such collections are naturally rich in variation, adding ambiguity to the notoriously difficult problem of correspondence computation. We leverage the robustness of correspondences between similar shapes to address the difficulties associated with this problem. In our approach, pairs of similar shapes are extracted from the collection, analyzed and matched in an efficient and reliable manner, culminating in the construction of a network of correspondences that connects the entire collection. The correspondence between any pair of shapes then amounts to a simple propagation along the minimax path between the two shapes in the network. At the heart of our approach is the introduction of a robust, structure-oriented shape matching method. Leveraging the idea of projective analysis, we partition 2D projections of a shape to obtain a set of 1D ordered regions, which are both simple and efficient to match. We lift the matched projections back to the 3D domain to obtain a pairwise shape correspondence. The emphasis given to structural compatibility is a central tool in estimating the reliability and completeness of a computed correspondence, uncovering any non-negligible semantic discrepancies that may exist between shapes. These detected differences are a deciding factor in the establishment of a network aiming to capture local similarities. We demonstrate that the combination of the presented observations into a co-analysis method allows us to establish reliable correspondences among shapes within large collections.

We develop a new kind of "space-filling" curves, connected Fermat spirals , and show their compelling properties as a tool path fill pattern for layered fabrication. Unlike classical space-filling curves such as the Peano or Hilbert curves, which constantly wind and bind to preserve locality, connected Fermat spirals are formed mostly by long, low-curvature paths. This geometric property, along with continuity, influences the quality and efficiency of layered fabrication. Given a connected 2D region, we first decompose it into a set of sub-regions, each of which can be filled with a single continuous Fermat spiral. We show that it is always possible to start and end a Fermat spiral fill at approximately the same location on the outer boundary of the filled region. This special property allows the Fermat spiral fills to be joined systematically along a graph traversal of the decomposed sub-regions. The result is a globally continuous curve. We demonstrate that printing 2D layers following tool paths as connected Fermat spirals leads to efficient and quality fabrication, compared to conventional fill patterns.

We present a technique for designing three-dimensional- (3D) printed perforated lampshades that project continuous grayscale images onto the surrounding walls. Given the geometry of the lampshade and a target grayscale image, our method computes a distribution of tiny holes over the shell, such that the combined footprints of the light emanating through the holes form the target image on a nearby diffuse surface. Our objective is to approximate the continuous tones and the spatial detail of the target image to the extent possible within the constraints of the fabrication process. To ensure structural integrity, there are lower bounds on the thickness of the shell, the radii of the holes, and the minimal distances between adjacent holes. Thus, the holes are realized as thin tubes distributed over the lampshade surface. The amount of light passing through a single tube may be controlled by the tube’s radius and by its orientation (tilt angle). The core of our technique thus consists of determining a suitable configuration of the tubes: their distribution across the relevant portion of the lampshade, as well as the parameters (radius, tilt angle) of each tube. This is achieved by computing a capacity-constrained Voronoi tessellation over a suitably defined density function and embedding a tube inside the maximal inscribed circle of each tessellation cell.

We present a novel system for browsing through a very large set of images according to similarity. The images are dynamically placed on a 2D canvas next to their nearest neighbors in a high-dimensional feature space. The layout and choice of images is generated on-the-fly during user interaction, reflecting the user's navigation tendencies and interests. This intuitive solution for image browsing provides a continuous experience of navigating through an infinite 2D grid arranged by similarity. In contrast to common multidimensional embedding methods, our solution does not entail an upfront creation of a full global map. Image map generation is dynamic, fast and scalable, independent of the number of images in the dataset, and seamlessly supports online updates to the dataset. Thus, the technique is a viable solution for massive and constantly varying datasets consisting of millions of images. Evaluation of our approach shows that when using DynamicMaps, users viewed many more images per minute compared to a standard relevance feedback interface, suggesting that it supports more fluid and natural interaction that enables easier and faster movement in the image space. Most users preferred DynamicMaps, indicating it is more exploratory, better supports serendipitous browsing and more fun to use

In this paper, we introduce a spherical embedding technique to position a given set of silhouettes of an object as observed from a set of cameras arbitrarily positioned around the object. Our technique estimates dissimilarities among the silhouettes and embeds them directly in the rotation space SO(3). The embedding is obtained by an optimization scheme applied over the rotations represented with exponential maps. Since the measure for inter-silhouette dissimilarities contains many outliers, our key idea is to perform the embedding by only using a subset of the estimated dissimilarities. We present a technique that carefully screens for inlier-distances, and the pairwise scaled dissimilarities are embedded in a spherical space, diffeomorphic to SO(3). We show that our method outperforms spherical MDS embedding, demonstrate its performance on various multi-view sets, and highlight its robustness to outliers.

Abstract We present a distillation algorithm which operates on a large, unstructured, and noisy collection of internet images returned from an online object query. We introduce the notion of a distilled set, which is a clean, coherent, and structured subset of inlier images. In addition, the object of interest is properly segmented out throughout the distilled set. Our approach is unsupervised, built on a novel clustering scheme, and solves the distillation and object segmentation problems simultaneously. In essence, instead of distilling the collection of images, we distill a collection of loosely cutout foreground “shapes”, which may or may not contain the queried object. Our key observation, which motivated our clustering scheme, is that outlier shapes are expected to be random in nature, whereas, inlier shapes, which do tightly enclose the object of interest, tend to be well supported by similar shapes captured in similar views. We analyze the commonalities among candidate foreground segments, without aiming to analyze their semantics, but simply by clustering similar shapes and considering only the most significant clusters representing non‐trivial shapes. We show that when tuned conservatively, our distillation algorithm is able to extract a near perfect subset of true inliers. Furthermore, we show that our technique scales well in the sense that the precision rate remains high, as the collection grows. We demonstrate the utility of our distillation results with a number of interesting graphics applications.

Abstract We introduce a novel method for enabling stereoscopic viewing of a scene from a single pre‐segmented image. Rather than attempting full 3D reconstruction or accurate depth map recovery, we hallucinate a rough approximation of the scene's 3D model using a number of simple depth and occlusion cues and shape priors. We begin by depth‐sorting the segments, each of which is assumed to represent a separate object in the scene, resulting in a collection of depth layers. The shapes and textures of the partially occluded segments are then completed using symmetry and convexity priors. Next, each completed segment is converted to a union of generalized cylinders yielding a rough 3D model for each object. Finally, the object depths are refined using an iterative ground fitting process. The hallucinated 3D model of the scene may then be used to generate a stereoscopic image pair, or to produce images from novel viewpoints within a small neighborhood of the original view. Despite the simplicity of our approach, we show that it compares favorably with state‐of‐the‐art depth ordering methods. A user study was conducted showing that our method produces more convincing stereoscopic images than existing semi‐interactive and automatic single image depth recovery methods.

Abstract Enhancing the self‐symmetry of a shape is of fundamental aesthetic virtue. In this paper, we are interested in recovering the aesthetics ofintrinsicreflection symmetries, where an asymmetric shape is symmetrized while keeping its general pose and perceived dynamics. The key challenge to intrinsic symmetrization is that the input shape has only approximate reflection symmetries, possibly far from perfect. The main premise of our work is that curve skeletons provide a concise and effective shape abstraction for analyzing approximate intrinsic symmetries as well as symmetrization. By measuring intrinsic distances over a curve skeleton for symmetry analysis, symmetrizing the skeleton, and then propagating the symmetrization from skeleton to shape, our approach to shape symmetrization isskeleton‐intrinsic. Specifically, given an input shape and an extracted curve skeleton, we introduce the notion of abackboneas the path in the skeleton graph about which a self‐matching of the input shape is optimal. We define an objective function for the reflective self‐matching and develop an algorithm based on genetic programming to solve the global search problem for the backbone. The extracted backbone then guides the symmetrization of the skeleton, which in turn, guides the symmetrization of the whole shape. We show numerous intrinsic symmetrization results of hand drawn sketches and artist‐modeled or reconstructed 3D shapes, as well as several applications of skeleton‐intrinsic symmetrization of shapes.

The multitude of cameras constantly present nowadays redefines the meaning of capturing an event and the meaning of sharing this event with others. The images are frequently uploaded to a common platform, and the image navigation challenge naturally arises. We introduce RingIt : a spectral technique for recovering the spatial order of a set of still images capturing an event taken by a group of people situated around the event. We assume a nearly instantaneous event, such as an interesting moment in a performance captured by the digital cameras and smartphones of the surrounding crowd. The ordering method extracts the K-nearest neighbors (KNN) of each image from a rough all-pairs dissimilarity estimate. The KNN dissimilarities are refined to form a sparse weighted Laplacian, and a spectral analysis then yields a ring angle for each image. The spatial order is recovered by sorting the obtained ring angles. The ordering of the unorganized set of images allows for a sequential display of the captured object. We demonstrate our technique on a number of sets capturing momentary events, where the images were acquired with low-quality consumer cameras by a group of people positioned around the event.

We pose the decompose-and-pack or DAP problem, which tightly combines shape decomposition and packing. While in general, DAP seeks to decompose an input shape into a small number of parts which can be efficiently packed, our focus is geared towards 3D printing. The goal is to optimally decompose-and-pack a 3D object into a printing volume to minimize support material, build time, and assembly cost. We present Dapper , a global optimization algorithm for the DAP problem which can be applied to both powder- and FDM-based 3D printing. The solution search is top-down and iterative. Starting with a coarse decomposition of the input shape into few initial parts, we progressively pack a pile in the printing volume, by iteratively docking parts, possibly while introducing cuts, onto the pile. Exploration of the search space is via a prioritized and bounded beam search , with breadth and depth pruning guided by local and global DAP objectives. A key feature of Dapper is that it works with pyramidal primitives, which are packing- and printing-friendly. Pyramidal shapes are also more general than boxes to reduce part counts, while still maintaining a suitable level of simplicity to facilitate DAP optimization. We demonstrate printing efficiency gains achieved by Dapper, compare to state-of-the-art alternatives, and show how fabrication criteria such as cut area and part size can be easily incorporated into our solution framework to produce more physically plausible fabrications.

We introduce JumpCut, a new mask transfer and interpolation method for interactive video cutout. Given a source frame for which a foreground mask is already available, we compute an estimate of the foreground mask at another, typically non-successive, target frame. Observing that the background and foreground regions typically exhibit different motions, we leverage these differences by computing two separate nearest-neighbor fields (split-NNF) from the target to the source frame. These NNFs are then used to jointly predict a coherent labeling of the pixels in the target frame. The same split-NNF is also used to aid a novel edge classifier in detecting silhouette edges (S-edges) that separate the foreground from the background. A modified level set method is then applied to produce a clean mask, based on the pixel labels and the S-edges computed by the previous two steps. The resulting mask transfer method may also be used for coherently interpolating the foreground masks between two distant source frames. Our results demonstrate that the proposed method is significantly more accurate than the existing state-of-the-art on a wide variety of video sequences. Thus, it reduces the required amount of user effort, and provides a basis for an effective interactive video object cutout tool.

Furniture typically consists of assemblies of elongated and planar parts that are connected together by glue, nails, hinges, screws, or other means that do not encourage disassembly and re-assembly. An alternative approach is to use an interlocking mechanism, where the component parts tightly interlock with one another. The challenge in designing such a network of interlocking joints is that local analysis is insufficient to guarantee global interlocking, and there is a huge number of joint combinations that require an enormous exploration effort to ensure global interlocking. In this paper, we present a computational solution to support the design of a network of interlocking joints that form a globally-interlocking furniture assembly. The key idea is to break the furniture complex into an overlapping set of small groups, where the parts in each group are immobilized by a local key, and adjacent groups are further locked with dependencies. The dependency among the groups saves the effort of exploring the immobilization of every subset of parts in the assembly, thus allowing the intensive interlocking computation to be localized within each small group. We demonstrate the effectiveness of our technique on many globally-interlocking furniture assemblies of various shapes and complexity.

Computing similarities or distances between 3D shapes is a crucial building block for numerous tasks, including shape retrieval, exploration and classification. Current state-of-the-art distance measures mostly consider the overall appearance of the shapes and are less sensitive to fine changes in shape structure or geometry. We presentshape edit distance(SHED) that measures the amount of effort needed to transform one shape into the other, in terms of re-arranging the parts of one shape to match the parts of the other shape, as well as possibly adding and removing parts. The shape edit distance takes into account both the similarity of the overall shape structure and the similarity of individual parts of the shapes. We show that SHED is favorable to state-of-the-art distance measures in a variety of applications and datasets, and is especially successful in scenarios where detecting fine details of the shapes is important, such as shape retrieval and exploration.

Both 3D models and 2D images contain a wealth of information about everyday objects in our environment. However, it is difficult to semantically link together these two media forms, even when they feature identical or very similar objects. We propose a joint embedding space populated by both 3D shapes and 2D images of objects, where the distances between embedded entities reflect similarity between the underlying objects. This joint embedding space facilitates comparison between entities of either form, and allows for cross-modality retrieval. We construct the embedding space using 3D shape similarity measure, as 3D shapes are more pure and complete than their appearance in images, leading to more robust distance metrics. We then employ a Convolutional Neural Network (CNN) to "purify" images by muting distracting factors. The CNN is trained to map an image to a point in the embedding space, so that it is close to a point attributed to a 3D model of a similar object to the one depicted in the image. This purifying capability of the CNN is accomplished with the help of a large amount of training data consisting of images synthesized from 3D shapes. Our joint embedding allows cross-view image retrieval, image-based shape retrieval, as well as shape-based image retrieval. We evaluate our method on these retrieval tasks and show that it consistently out-performs state-of-the-art methods, and demonstrate the usability of a joint embedding in a number of additional applications.

In this paper, we present a consolidation method that is based on a new representation of 3D point sets. The key idea is to augment each surface point into a deep point by associating it with an inner point that resides on the meso-skeleton, which consists of a mixture of skeletal curves and sheets. The deep points representation is a result of a joint optimization applied to both ends of the deep points. The optimization objective is to fairly distribute the end points across the surface and the meso-skeleton, such that the deep point orientations agree with the surface normals. The optimization converges where the inner points form a coherent meso-skeleton, and the surface points are consolidated with the missing regions completed. The strength of this new representation stems from the fact that it is comprised of both local and non-local geometric information. We demonstrate the advantages of the deep points consolidation technique by employing it to consolidate and complete noisy point-sampled geometry with large missing parts.

Decomposing a complex shape into geometrically simple primitives is a fundamental problem in geometry processing. We are interested in a shape decomposition problem where the simple primitives sought are generalized cylinders , which are ubiquitous in both organic forms and man-made artifacts. We introduce a quantitative measure of cylindricity for a shape part and develop a cylindricity-driven optimization algorithm, with a global objective function, for generalized cylinder decomposition. As a measure of geometric simplicity and following the minimum description length principle, cylindricity is defined as the cost of representing a cylinder through skeletal and cross-section profile curves. Our decomposition algorithm progressively builds local to non-local cylinders, which form over-complete covers of the input shape. The over-completeness of the cylinder covers ensures a conservative buildup of the cylindrical parts, leaving the final decision on decomposition to global optimization. We solve the global optimization by finding an exact cover, which optimizes the global objective function. We demonstrate results of our optimal decomposition algorithm on numerous examples and compare with other alternatives.

Abstract We present a semi‐automatic method for reconstructing flower models from a single photograph. Such reconstruction is challenging since the 3D structure of a flower can appear ambiguous in projection. However, the flower head typically consists of petals embedded in 3D space that share similar shapes and form certain level of regular structure. Our technique employs these assumptions by first fitting a cone and subsequently a surface of revolution to the flower structure and then computing individual petal shapes from their projection in the photo. Flowers with multiple layers of petals are handled through processing different layers separately. Occlusions are dealt with both within and between petal layers. We show that our method allows users to quickly generate a variety of realistic 3D flowers from photographs and to animate an image using the underlying models reconstructed from our method.

Abstract Extracting semantically related parts across models remains challenging, especially without supervision. The common approach is to co‐analyze a model collection, while assuming the existence of descriptive geometric features that can directly identify related parts. In the presence of large shape variations, common geometric features, however, are no longer sufficiently descriptive. In this paper, we explore an indirect top‐down approach, where instead of part geometry, part arrangements extracted from each model are compared. The key observation is that while a direct comparison of part geometry can be ambiguous, part arrangements, being higher level structures, remain consistent, and hence can be used to discover latent commonalities among semantically related shapes. We show that our indirect analysis leads to the detection of recurring arrangements of parts, which are otherwise difficult to discover in a direct unsupervised setting. We evaluate our algorithm on ground truth datasets and report advantages over geometric similarity‐based bottom‐up co‐segmentation algorithms.

We introduce focal points for characterizing, comparing, and organizing collections of complex and heterogeneous data and apply the concepts and algorithms developed to collections of 3D indoor scenes. We represent each scene by a graph of its constituent objects and define focal points as representative substructures in a scene collection. To organize a heterogeneous scene collection, we cluster the scenes based on a set of extracted focal points: scenes in a cluster are closely connected when viewed from the perspective of the representative focal points of that cluster. The key concept of representativity requires that the focal points occur frequently in the cluster and that they result in a compact cluster. Hence, the problem of focal point extraction is intermixed with the problem of clustering groups of scenes based on their representative focal points. We present a co-analysis algorithm which interleaves frequent pattern mining and subspace clustering to extract a set of contextual focal points which guide the clustering of the scene collection. We demonstrate advantages of focal-centric scene comparison and organization over existing approaches, particularly in dealing with hybrid scenes, scenes consisting of elements which suggest membership in different semantic categories.

A shape is pyramidal if it has a flat base with the remaining boundary forming a height function over the base. Pyramidal shapes are optimal for molding, casting, and layered 3D printing. However, many common objects are not pyramidal. We introduce an algorithm for approximate pyramidal shape decomposition . The general exact pyramidal decomposition problem is NP-hard. We turn this problem into an NP-complete problem which admits a practical solution. Specifically, we link pyramidal decomposition to the Exact Cover Problem (ECP). Given an input shape S , we develop clustering schemes to derive a set of building blocks for approximate pyramidal parts of S . The building blocks are then combined to yield a set of candidate pyramidal parts. Finally, we employ Knuth's Algorithm X over the candidate parts to obtain solutions to ECP as pyramidal shape decompositions. Our solution is equally applicable to 2D or 3D shapes, and to shapes with polygonal or smooth boundaries, with or without holes. We demonstrate our algorithm on numerous shapes and evaluate its performance.

We present a shape segmentation method for complete and incomplete shapes. The key idea is to directly optimize the decomposition based on a characterization of the expected geometry of a part in a shape. Rather than setting the number of parts in advance, we search for the smallest number of parts that admit the geometric characterization of the parts. The segmentation is based on an intermediate-level analysis, where first the shape is decomposed into approximate convex components, which are then merged into consistent parts based on a nonlocal geometric signature. Our method is designed to handle incomplete shapes, represented by point clouds. We show segmentation results on shapes acquired by a range scanner, and an analysis of the robustness of our method to missing regions. Moreover, our method yields results that are comparable to state-of-the-art techniques evaluated on complete shapes.

The emergence of low-cost 3D printers steers the investigation of new geometric problems that control the quality of the fabricated object. In this paper, we present a method to reduce the material cost and weight of a given object while providing a durable printed model that is resistant to impact and external forces. We introduce a hollowing optimization algorithm based on the concept of honeycomb-cells structure. Honeycombs structures are known to be of minimal material cost while providing strength in tension. We utilize the Voronoi diagram to compute irregular honeycomb-like volume tessellations which define the inner structure. We formulate our problem as a strength--to--weight optimization and cast it as mutually finding an optimal interior tessellation and its maximal hollowing subject to relieve the interior stress. Thus, our system allows to build-to-last 3D printed objects with large control over their strength-to-weight ratio and easily model various interior structures. We demonstrate our method on a collection of 3D objects from different categories. Furthermore, we evaluate our method by printing our hollowed models and measure their stress and weights.

We introduce a meta-representation that represents the essence of a family of shapes. The meta-representation learns the configurations of shape parts that are common across the family, and encapsulates this knowledge with a system of geometric distributions that encode relative arrangements of parts. Thus, instead of predefined priors, what characterizes a shape family is directly learned from the set of input shapes. The meta-representation is constructed from a set of co-segmented shapes with known correspondence. It can then be used in several applications where we seek to preserve the identity of the shapes as members of the family. We demonstrate applications of the meta-representation in exploration of shape repositories, where interesting shape configurations can be examined in the set; guided editing, where models can be edited while maintaining their familial traits; and coupled editing, where several shapes can be collectively deformed by directly manipulating the distributions in the meta-representation. We evaluate the efficacy of the proposed representation on a variety of shape collections.

We present a quality-driven, Poisson-guided autonomous scanning method. Unlike previous scan planning techniques, we do not aim to minimize the number of scans needed to cover the object's surface, but rather to ensure the high quality scanning of the model. This goal is achieved by placing the scanner at strategically selected Next-Best-Views (NBVs) to ensure progressively capturing the geometric details of the object, until both completeness and high fidelity are reached. The technique is based on the analysis of a Poisson field and its geometric relation with an input scan. We generate a confidence map that reflects the quality/fidelity of the estimated Poisson iso-surface. The confidence map guides the generation of a viewing vector field, which is then used for computing a set of NBVs. We applied the algorithm on two different robotic platforms, a PR2 mobile robot and a one-arm industry robot. We demonstrated the advantages of our method through a number of autonomous high quality scannings of complex physical objects, as well as performance comparisons against state-of-the-art methods.

With significant data missing in a point scan, reconstructing a complete surface with sufficient geometric and topological fidelity is highly challenging. We present an interactive technique for surface reconstruction from incomplete and sparse scans of 3D objects possessing sharp features. A fundamental premise of our interaction paradigm is that directly editing data in 3D is not only counterintuitive but also ineffective, while working with 1D entities (i.e., curves) is a lot more manageable. To this end, we factor 3D editing into two "orthogonal" interactions acting on skeletal and profile curves of the underlying shape, controlling its topology and geometric features, respectively. For surface completion, we introduce a novel skeleton-driven morph-to-fit , or morfit , scheme which reconstructs the shape as an ensemble of generalized cylinders. Morfit is a hybrid operator which optimally interpolates between adjacent curve profiles (the "morph") and snaps the surface to input points (the "fit"). The interactive reconstruction iterates between user edits and morfit to converge to a desired final surface. We demonstrate various interactive reconstructions from point scans with sharp features and significant missing data.

We introduce a method for replacing the background in a video of a moving foreground subject, when both the source video capturing the subject, and the target video capturing the new background scene, are natural videos, casually captured using a freely moving hand-held camera. We assume that the foreground subject has already been extracted, and focus on the challenging task of generating a video with a new background, such that the new background motion appears compatible with the original one. Failure to match the motion results in disturbing slippage or moonwalk artifacts, where the subject's feet appear to slide or slip over the ground. While matching the motion across the entire frame is impossible for scenes with differing geometry, we aim to match the local motion of the ground in the vicinity of the subject. This is achieved by reordering and warping the available target background frames in a manner that optimizes a suitably designed objective function.

In this paper, we introduce a new approach to constrained clustering which treats the constraints as features. Our method augments the original feature space with additional dimensions, each of which derived from a given Cannot-link constraints. The specified Cannot-link pair gets extreme coordinates values, and the rest of the points get coordinate values that express their spatial influence from the specified constrained pair. After augmenting all the new features, a standard unconstrained clustering algorithm can be performed, like k-means or spectral clustering. We demonstrate the efficacy of our method for active semi-supervised learning applied to image segmentation and compare it to alternative methods. We also evaluate the performance of our method on the four most commonly evaluated datasets from the UCI machine learning repository.

Summary form only given. An interesting question is whether a machine can assist humans in being creative and inspire a user during the creation of 3D models or a shape in general. One possible means to achieve this is through a design gallery which presents a variety of computed suggestive designs from which the user can pick the ones he likes the best. The ensuing challenge is how to come up with intriguing suggestions which inspire creativity, rather than banal suggestions which stall the design process. In my talk I will discuss about the notion of creative modeling, synthesis of inspiring examples, the analysis of a set, and show a number of recent works that step towards this end.

Abstract We define the convexity rank of a set of points to be the portion of mutually visible pairs of points out of the total number of pairs. Based on this definition of weak convexity, we introduce a spectral method that decomposes a given shape into weakly convex regions. The decomposition is applied without explicitly measuring the convexity rank. The method merely amounts to a spectral clustering of a matrix representing the all‐pairs line of sight. Our method can be directly applied on an oriented point cloud and does not require any topological information, nor explicit concavity or convexity measures. We demonstrate the efficiency of our algorithm on a large number of examples and compare them qualitatively with competitive approaches.

Abstract Large datasets of 3D objects require an intuitive way to browse and quickly explore shapes from the collection. We present a dynamic map of shapes where similar shapes are placed next to each other. Similarity between 3D models exists in a high dimensional space which cannot be accurately expressed in a two dimensional map. We solve this discrepancy by providing a local map with pan capabilities and a user interface that resembles an online experience of navigating through geographical maps. As the user navigates through the map, new shapes appear which correspond to the specific navigation tendencies and interests of the user, while maintaining a continuous browsing experience. In contrast with state of the art methods which typically reduce the search space by selecting constraints or employing relevance feedback, our method enables exploration of large sets without constraining the search space, allowing the user greater creativity and serendipity. A user study evaluation showed a strong preference of users for our method over a standard relevance feedback method.

Abstract The word ‘style’ can be interpreted in so many different ways in so many different contexts. To provide a general analysis and understanding of styles is a highly challenging problem. We pose the open question ‘how to extract styles from geometric shapes?’ and address one instance of the problem. Specifically, we present an unsupervised algorithm for identifying curve styles in a set of shapes. In our setting, a curve style is explicitly represented by a mode of curve features appearing along the 2D silhouettes of the shapes in the set. Unlike previous attempts, we do not rely on any preconceived conceptual characterisations, for example, via specific shape descriptors, to define what is or is not a style. Our definition of styles is data‐dependent; it depends on the input set but we do not require computing a shape correspondence across the set. We provide an operational definition of curve styles which focuses on separating curve features that represent styles from curve features that are content revealing. To this end, we develop a novel formulation and associated algorithm for style‐content separation. The analysis is based on a feature‐shape association matrix (FSM) whose rows correspond to modes of curve features, columns to shapes in the set, and each entry expresses the extent a feature mode is present in a shape. We make several assumptions to drive style‐content separation which only involve properties of, and relations between, rows of the FSM. Computationally, our algorithm only requires row‐wise correlation analysis in the FSM and a heuristic solution of an instance of the set cover problem. Results are demonstrated on several data sets showing the identification of curve styles. We also develop and demonstrate several style‐related applications including style exaggeration, removal, blending, and style transfer for 2D shape synthesis.

Abstract Modeling 3D objects from sketches is a process that requires several challenging problems including segmentation, recognition and reconstruction. Some of these tasks are harder for humans and some are harder for the machine. At the core of the problem lies the need for semantic understanding of the shape's geometry from the sketch. In this paper we propose a method to model 3D objects from sketches by utilizing humans specifically for semantic tasks that are very simple for humans and extremely difficult for the machine, while utilizing the machine for tasks that are harder for humans. The user assists recognition and segmentation by choosing and placing specific geometric primitives on the relevant parts of the sketch. The machine first snaps the primitive to the sketch by fitting its projection to the sketch lines, and then improves the model globally by inferringgeosemanticconstraints that link the different parts. The fitting occurs in real‐time, allowing the user to be only as precise as needed to have a good starting configuration for this non‐convex optimization problem. We evaluate the accessibility of our approach with a user study.

Abstract Designing 3D objects from scratch is difficult, especially when the user intent is fuzzy and lacks a clear target form. We facilitate design by providing reference and inspiration from existing model contexts. We rethink model design as navigating through different possible combinations of part assemblies based on a large collection of pre‐segmented 3D models. We propose an interactive sketch‐to‐design system, where the user sketches prominent features of parts to combine. The sketched strokes are analysed individually, and more importantly, in context with the other parts to generate relevant shape suggestions via adesign galleryinterface. As a modelling session progresses and more parts get selected, contextual cues become increasingly dominant, and the model quickly converges to a final form. As a key enabler, we use pre‐learned part‐based contextual information to allow the user to quickly explore different combinations of parts. Our experiments demonstrate the effectiveness of our approach for efficiently designing new variations from existing shape collections.

Abstract As collections of 3D models continue to grow, reusing model parts allows generation of novel model variations. Naïvely swapping parts across models, however, leads to implausible results, especially when mixing parts across different model families. Hence, the user has to manually ensure that the final model remains functionally valid. We claim that certain symmetric functional arrangements (sFarr‐s), which are special arrangements among symmetrically related substructures, bear close relation to object functions. Hence, we propose a purely geometric approach based on such substructures to match, replace, and position triplets of parts to create non‐trivial, yet functionally plausible, model variations. We demonstrate that starting even from a small set of models such a simple geometric approach can produce a diverse set of non‐trivial and plausible model variations.

We introduce L 1 - medial skeleton as a curve skeleton representation for 3D point cloud data. The L 1 -median is well-known as a robust global center of an arbitrary set of points. We make the key observation that adapting L 1 -medians locally to a point set representing a 3D shape gives rise to a one-dimensional structure, which can be seen as a localized center of the shape. The primary advantage of our approach is that it does not place strong requirements on the quality of the input point cloud nor on the geometry or topology of the captured shape. We develop a L 1 -medial skeleton construction algorithm, which can be directly applied to an unoriented raw point scan with significant noise, outliers, and large areas of missing data. We demonstrate L 1 -medial skeletons extracted from raw scans of a variety of shapes, including those modeling high-genus 3D objects, plant-like structures, and curve networks.

Points acquired by laser scanners are not intrinsically equipped with normals, which are essential to surface reconstruction and point set rendering using surfels. Normal estimation is notoriously sensitive to noise. Near sharp features, the computation of noise-free normals becomes even more challenging due to the inherent undersampling problem at edge singularities. As a result, common edge-aware consolidation techniques such as bilateral smoothing may still produce erroneous normals near the edges. We propose a resampling approach to process a noisy and possibly outlier-ridden point set in an edge-aware manner. Our key idea is to first resample away from the edges so that reliable normals can be computed at the samples, and then based on reliable data, we progressively resample the point set while approaching the edge singularities. We demonstrate that our Edge-Aware Resampling (EAR) algorithm is capable of producing consolidated point sets with noise-free normals and clean preservation of sharp features. We also show that EAR leads to improved performance of edge-aware reconstruction methods and point set rendering techniques.

Concocting a plausible composition from several non-overlapping image pieces, whose relative positions are not fixed in advance and without having the benefit of priors, can be a daunting task. Here we propose such a method, starting with a set of sloppily pasted image pieces with gaps between them. We first extract salient curves that approach the gaps from non-tangential directions, and use likely correspondences between pairs of such curves to guide a novel tele-registration method that simultaneously aligns all the pieces together. A structure-driven image completion technique is then proposed to fill the gaps, allowing the subsequent employment of standard in-painting tools to finish the job.

We introduce an interactive technique for manipulating simple 3D shapes based on extracting them from a single photograph. Such extraction requires understanding of the components of the shape, their projections, and relations. These simple cognitive tasks for humans are particularly difficult for automatic algorithms. Thus, our approach combines the cognitive abilities of humans with the computational accuracy of the machine to solve this problem. Our technique provides the user the means to quickly create editable 3D parts---human assistance implicitly segments a complex object into its components, and positions them in space. In our interface, three strokes are used to generate a 3D component that snaps to the shape's outline in the photograph, where each stroke defines one dimension of the component. The computer reshapes the component to fit the image of the object in the photograph as well as to satisfy various inferred geometric constraints imposed by its global 3D structure. We show that with this intelligent interactive modeling tool, the daunting task of object extraction is made simple. Once the 3D object has been extracted, it can be quickly edited and placed back into photos or 3D scenes, permitting object-driven photo editing tasks which are impossible to perform in image-space. We show several examples and present a user study illustrating the usefulness of our technique.

We present a method for organizing a heterogeneous collection of 3D shapes for overview and exploration. Instead of relying on quantitative distances, which may become unreliable between dissimilar shapes, we introduce aqualitativeanalysis which utilizes multiple distance measures but only in cases where the measures can be reliably compared. Our analysis is based on the notion ofquartets, each defined by two pairs of shapes, where the shapes in each pair are close to each other, but far apart from the shapes in the other pair. Combining the information from many quartets computed across a shape collection using several distance measures, we create a hierarchical structure we callcategorization treeof the shape collection. This tree satisfies the topological (qualitative) constraints imposed by the quartets creating an effective organization of the shapes. We present categorization trees computed on various collections of shapes and compare them to ground truth data from human categorization. We further introduce the concept ofdegree of separationchart for every shape in the collection and show the effectiveness of using it for interactive shapes exploration.

We introduce an unsupervised co-hierarchical analysis of a set of shapes, aimed at discovering their hierarchical part structures and revealing relations between geometrically dissimilar yet functionally equivalent shape parts across the set. The core problem is that of representative co-selection . For each shape in the set, one representative hierarchy (tree) is selected from among many possible interpretations of the hierarchical structure of the shape. Collectively, the selected tree representatives maximize the within-cluster structural similarity among them. We develop an iterative algorithm for representative co-selection. At each step, a novel cluster-and-select scheme is applied to a set of candidate trees for all the shapes. The tree-to-tree distance for clustering caters to structural shape analysis by focusing on spatial arrangement of shape parts, rather than their geometric details. The final set of representative trees are unified to form a structural co-hierarchy. We demonstrate co-hierarchical analysis on families of man-made shapes exhibiting high degrees of geometric and finer-scale structural variabilities.

Studying growth and development of plants is of central importance in botany. Current quantitative are either limited to tedious and sparse manual measurements, or coarse image-based 2D measurements. Availability of cheap and portable 3D acquisition devices has the potential to automate this process and easily provide scientists with volumes of accurate data, at a scale much beyond the realms of existing methods. However, during their development, plants grow new parts (e.g., vegetative buds) and bifurcate to different components --- violating the central incompressibility assumption made by existing acquisition algorithms, which makes these algorithms unsuited for analyzing growth. We introduce a framework to study plant growth, particularly focusing on accurate localization and tracking topological events like budding and bifurcation. This is achieved by a novel forward-backward analysis, wherein we track robustly detected plant components back in time to ensure correct spatio-temporal event detection using a locally adapting threshold. We evaluate our approach on several groups of time lapse scans, often ranging from days to weeks, on a diverse set of plant species and use the results to animate static virtual plants or directly attach them to physical simulators.

A reciprocal frame (RF) is a self-supported three-dimensional structure made up of three or more sloping rods, which form a closed circuit, namely an RF-unit. Large RF-structures built as complex grillages of one or a few similar RF-units have an intrinsic beauty derived from their inherent self-similar and highly symmetric patterns. Designing RF-structures that span over large domains is an intricate and complex task. In this paper, we present an interactive computational tool for designing RF-structures over a 3D guiding surface, focusing on the aesthetic aspect of the design. There are three key contributions in this work. First, we draw an analogy between RF-structures and plane tiling with regular polygons, and develop a computational scheme to generate coherent RF-tessellations from simple grammar rules. Second, we employ a conformal mapping to lift the 2D tessellation over a 3D guiding surface, allowing a real-time preview and efficient exploration of wide ranges of RF design parameters. Third, we devise an optimization method to guarantee the collinearity of contact joints along each rod, while preserving the geometric properties of the RF-structure. Our tool not only supports the design of wide variety of RF pattern classes and their variations, but also allows preview and refinement through interactive controls.

We introduce projective analysis for semantic segmentation and labeling of 3D shapes. The analysis treats an input 3D shape as a collection of 2D projections, labels each projection by transferring knowledge from existing labeled images, and back-projects and fuses the labelings on the 3D shape. The image-space analysis involves matching projected binary images of 3D objects based on a novel bi-class Hausdorff distance . The distance is topology-aware by accounting for internal holes in the 2D figures and it is applied to piecewise-linearly warped object projections to compensate for part scaling and view discrepancies. Projective analysis simplifies the processing task by working in a lower-dimensional space, circumvents the requirement of having complete and well-modeled 3D shapes, and addresses the data challenge for 3D shape analysis by leveraging the massive available image data. A large and dense labeled set ensures that the labeling of a given projected image can be inferred from closely matched labeled images. We demonstrate semantic labeling of imperfect (e.g., incomplete or self-intersecting) 3D models which would be otherwise difficult to analyze without taking the projective analysis approach.

We present an algorithm for hierarchical and layered analysis of irregular facades, seeking a high-level understanding of facade structures. By introducing layering into the analysis, we no longer view a facade as a flat structure, but allow it to be structurally separated into depth layers, enabling more compact and natural interpretations of building facades. Computationally, we perform a symmetry-driven search for an optimal hierarchical decomposition defined by split and layering operations applied to an input facade. The objective is symmetry maximization , i.e., to maximize the sum of symmetry of the substructures resulting from recursive decomposition. To this end, we propose a novel integral symmetry measure, which behaves well at both ends of the symmetry spectrum by accounting for all partial symmetries in a discrete structure. Our analysis results in a structural representation, which can be utilized for structural editing and exploration of building facades.

Abstract Many photographs are taken in perspective. Techniques for rectifying resulting perspective distortions typically rely on the existence of parallel lines in the scene. In scenarios where such parallel lines are hard to automatically extract or manually annotate, the unwarping process remains a challenge. In this paper, we introduce an automatic algorithm to rectifying images containing textures of repeated elements lying on an unknown plane. We unwrap the input by maximizing for image self‐similarity over the space of homography transformations. We map a set of detected regional descriptors to surfaces in a transformation space, compute the intersection points among triplets of such surfaces, and then use consensus among the projected intersection points to extract the correcting transform. Our algorithm is global, robust, and does not require explicit or accurate detection of similar elements. We evaluate our method on a variety of challenging textures and images. The rectified outputs are directly useful for various tasks including texture synthesis, image completion, etc.

We present an automatic shape composition method to fuse two shape parts which may not overlap and possibly contain sharp features, a scenario often encountered when modeling man-made objects. At the core of our method is a novel field-guided approach to automatically align two input parts in a feature-conforming manner. The key to our field-guided shape registration is a natural continuation of one part into the ambient field as a means to introduce an overlap with the distant part, which then allows a surface-to-field registration. The ambient vector field we compute is feature-conforming; it characterizes a piecewise smooth field which respects and naturally extrapolates the surface features. Once the two parts are aligned, gap filling is carried out by spline interpolation between matching feature curves followed by piecewise smooth least-squares surface reconstruction. We apply our algorithm to obtain feature-conforming shape composition on a variety of models and demonstrate generality of the method with results on parts with or without overlap and with or without salient features.

Human Computation (HC) utilizes humans to solve problems or carry out tasks that are hard for pure computational algorithms. Many graphics and vision problems have such tasks. Previous HC approaches mainly focus on generating data in batch, to gather benchmarks, or perform surveys demanding nontrivial interactions. We advocate a tighter integration of human computation into online, interactive algorithms. We aim to distill the differences between humans and computers and maximize the advantages of both in one algorithm. Our key idea is to decompose such a problem into a massive number of very simple, carefully designed, human micro-tasks that are based on perception , and whose answers can be combined algorithmically to solve the original problem. Our approach is inspired by previous work on micro-tasks and perception experiments. We present three specific examples for the design of micro perceptual human computation algorithms to extract depth layers and image normals from a single photograph, and to augment an image with high-level semantic information such as symmetry.

We introduce the geometric problem of stackabilization : how to geometrically modify a 3D object so that it is more amenable to stacking. Given a 3D object and a stacking direction, we define a measure of stackability, which is derived from the gap between the lower and upper envelopes of the object in a stacking configuration along the stacking direction. The main challenge in stackabilization lies in the desire to modify the object's geometry only subtly so that the intended functionality and aesthetic appearance of the original object are not significantly affected. We present an automatic algorithm to deform a 3D object to meet a target stackability score using energy minimization. The optimized energy accounts for both the scales of the deformation parameters as well as the preservation of pre-existing geometric and structural properties in the object, e. g., symmetry, as a means of maintaining its functionality. We also present an intelligent editing tool that assists a modeler when modifying a given 3D object to improve its stackability. Finally, we explore a few fun variations of the stackabilization problem.

Interlocking puzzles are very challenging geometric problems with the fascinating property that once we solve one by putting together the puzzle pieces, the puzzle pieces interlock with one another, preventing the assembly from falling apart. Though interlocking puzzles have been known for hundreds of years, very little is known about the governing mechanics. Thus, designing new interlocking geometries is basically accomplished with extensive manual effort or expensive exhaustive search with computers. In this paper, we revisit the notion of interlocking in greater depth, and devise a formal method of the interlocking mechanics. From this, we can develop a constructive approach for devising new interlocking geometries that directly guarantees the validity of the interlocking instead of exhaustively testing it. In particular, we focus on an interesting subclass of interlocking puzzles that are recursive in the sense that the assembly of puzzle pieces can remain an interlocking puzzle also after sequential removal of pieces; there is only one specific sequence of assembling, or disassembling, such a puzzle. Our proposed method can allow efficient generation of recursive interlocking geometries of various complexities, and by further realizing it with LEGO bricks, we can enable the hand-built creation of custom puzzle games.

Unsupervised co-analysis of a set of shapes is a difficult problem since the geometry of the shapes alone cannot always fully describe the semantics of the shape parts. In this paper, we propose a semi-supervised learning method where the user actively assists in the co-analysis by iteratively providing inputs that progressively constrain the system. We introduce a novel constrained clustering method based on a spring system which embeds elements to better respect their inter-distances in feature space together with the user-given set of constraints. We also present an active learning method that suggests to the user where his input is likely to be the most effective in refining the results. We show that each single pair of constraints affects many relations across the set. Thus, the method requires only a sparse set of constraints to quickly converge toward a consistent and error-free semantic labeling of the set.

We introduce set evolution as a means for creative 3D shape modeling, where an initial population of 3D models is evolved to produce generations of novel shapes. Part of the evolving set is presented to a user as a shape gallery to offer modeling suggestions. User preferences define the fitness for the evolution so that over time, the shape population will mainly consist of individuals with good fitness. However, to inspire the user's creativity, we must also keep the evolving set diverse. Hence the evolution is " fit and diverse ", drawing motivation from evolution theory. We introduce a novel part crossover operator which works at the finer-level part structures of the shapes, leading to significant variations and thus increased diversity in the evolved shape structures. Diversity is also achieved by explicitly compromising the fitness scores on a portion of the evolving population. We demonstrate the effectiveness of set evolution on man-made shapes. We show that selecting only models with high fitness leads to an elite population with low diversity. By keeping the population fit and diverse, the evolution can generate inspiring, and sometimes unexpected, shapes.

We present a method for fusing two acquisition modes, 2D photographs and 3D LiDAR scans, for depth-layer decomposition of urban facades. The two modes have complementary characteristics: point cloud scans are coherent and inherently 3D, but are often sparse, noisy, and incomplete; photographs, on the other hand, are of high resolution, easy to acquire, and dense, but view-dependent and inherently 2D, lacking critical depth information. In this paper we use photographs to enhance the acquired LiDAR data. Our key observation is that with an initial registration of the 2D and 3D datasets we can decompose the input photographs into rectified depth layers. We decompose the input photographs into rectangular planar fragments and diffuse depth information from the corresponding 3D scan onto the fragments by solving a multi-label assignment problem. Our layer decomposition enables accurate repetition detection in each planar layer, using which we propagate geometry, remove outliers and enhance the 3D scan. Finally, the algorithm produces an enhanced, layered, textured model. We evaluate our algorithm on complex multi-planar building facades, where direct autocorrelation methods for repetition detection fail. We demonstrate how 2D photographs help improve the 3D scans by exploiting data redundancy, and transferring high level structural information to (plausibly) complete large missing regions.

Abstract Classical approaches to shape correspondence base their computation purely on the properties, in particular geometric similarity, of the shapes in question. Their performance still falls far short of that of humans in challenging cases where corresponding shape parts may differ significantly in geometry or even topology. We stipulate that in these cases, shape correspondence by humans involves recognition of the shape parts where prior knowledge on the parts would play a more dominant role than geometric similarity. We introduce an approach to part correspondence which incorporates prior knowledge imparted by a training set of pre‐segmented, labeled models and combines the knowledge with content‐driven analysis based on geometric similarity between the matched shapes. First, the prior knowledge is learned from the training set in the form of per‐label classifiers. Next, given two query shapes to be matched, we apply the classifiers to assign a probabilistic label to each shape face. Finally, by means of a joint labeling scheme, the probabilistic labels are used synergistically with pairwise assignments derived from geometric similarity to provide the resulting part correspondence. We show that the incorporation of knowledge is especially effective in dealing with shapes exhibiting large intra‐class variations. We also show that combining knowledge and content analyses outperforms approaches guided by either attribute alone.

Abstract We review methods designed to compute correspondences between geometric shapes represented by triangle meshes, contours or point sets. This survey is motivated in part by recent developments in space–time registration, where one seeks a correspondence between non‐rigid and time‐varying surfaces, and semantic shape analysis, which underlines a recent trend to incorporate shape understanding into the analysis pipeline. Establishing a meaningful correspondence between shapes is often difficult because it generally requires an understanding of the structure of the shapes at both the local and global levels, and sometimes the functionality of the shape parts as well. Despite its inherent complexity, shape correspondence is a recurrent problem and an essential component of numerous geometry processing applications. In this survey, we discuss the different forms of the correspondence problem and review the main solution methods, aided by several classification criteria arising from the problem definition. The main categories of classification are defined in terms of the input and output representation, objective function and solution approach. We conclude the survey by discussing open problems and future perspectives.

Abstract Objects with many concavities are difficult to acquire using laser scanners. The highly concave areas are hard to access by a scanner due to occlusions by other components of the object. The resulting point scan typically suffers from large amounts of missing data. Methods that use surface‐based priors rely on local surface estimates and perform well only when filling small holes. When the holes become large, the reconstruction problem becomes severely under‐constrained, which necessitates the use of additional reconstruction priors. In this paper, we introduce weak volumetric priors which assume that the volume of a shape varies smoothly and that each point cloud sample is visible from outside the shape. Specifically, the union of view‐rays given by the scanner implicitly carves the exterior volume, while volumetric smoothness regularizes the internal volume. We incorporate these priors into a surface evolution framework where a new energy term defined by volumetric smoothness is introduced to handle large amount of missing data. We demonstrate the effectiveness of our method on objects exhibiting deep concavities, and show its general applicability over a broader spectrum of geometric scenario.

Abstract Recent shape editing techniques, especially for man‐made models, have gradually shifted focus from maintaining local, low‐level geometric features to preserving structural, high‐level characteristics like symmetry and parallelism. Such new editing goals typically require a pre‐processing shape analysis step to enable subsequent shape editing. Observing that most editing of shapes involves manipulating their constituent components, we introduce component‐wise controllers that are adapted to the component characteristics inferred from shape analysis. The controllers capture the natural degrees of freedom of individual components and thus provide an intuitive user interface for editing. A typical model usually results in a moderate number of controllers, allowing easy establishment of semantic relations among them by automatic shape analysis supplemented with user interaction. We propose a component‐wise propagation algorithm to automatically preserve the established inter‐relations while maintaining the defining characteristics of individual controllers and respecting the user‐specified modeling constraints. We extend these ideas to a hierarchical setup, allowing the user to adjust the tool complexity with respect to the desired modeling complexity. We demonstrate the effectiveness of our technique on a wide range of man‐made models with structural features, often containing multiple connected pieces.

Given a noisy and incomplete point set, we introduce a method that simultaneously recovers a set of locally fitted primitives along with their global mutual relations. We operate under the assumption that the data corresponds to a man-made engineering object consisting of basic primitives, possibly repeated and globally aligned under common relations. We introduce an algorithm to directly couple the local and global aspects of the problem. The local fit of the model is determined by how well the inferred model agrees to the observed data, while the global relations are iteratively learned and enforced through a constrained optimization. Starting with a set of initial RANSAC based locally fitted primitives, relations across the primitives such as orientation, placement, and equality are progressively learned and conformed to. In each stage, a set of feasible relations are extracted among the candidate relations, and then aligned to, while best fitting to the input data. The global coupling corrects the primitives obtained in the local RANSAC stage, and brings them to precise global alignment. We test the robustness of our algorithm on a range of synthesized and scanned data, with varying amounts of noise, outliers, and non-uniform sampling, and validate the results against ground truth, where available.

We present an algorithm for interactive structure-preserving retargeting of irregular 3D architecture models, offering the modeler an easy-to-use tool to quickly generate a variety of 3D models that resemble an input piece in its structural style. Working on a more global and structural level of the input, our technique allows and even encourages replication of its structural elements, while taking into account their semantics and expected geometric interrelations such as alignments and adjacency. The algorithm performs automatic replication and scaling of these elements while preserving their structures. Instead of formulating and solving a complex constrained optimization, we decompose the input model into a set of sequences, each of which is a 1D structure that is relatively straightforward to retarget. As the sequences are retargeted in turn, they progressively constrain the retargeting of the remaining sequences. We demonstrate interactivity and variability of results from our retargeting algorithm using many examples modeled after real-world architectures exhibiting various forms of irregularity.

We present a lobe-based tree representation for modeling trees. The new representation is based on the observation that the tree's foliage details can be abstracted into canonical geometry structures, termed lobe-textures. We introduce techniques to (i) approximate the geometry of given tree data and encode it into a lobe-based representation, (ii) decode the representation and synthesize a fully detailed tree model that visually resembles the input. The encoded tree serves as a light intermediate representation, which facilitates efficient storage and transmission of massive amounts of trees, e.g., from a server to clients for interactive applications in urban environments. The method is evaluated by both reconstructing laser scanned trees (given as point sets) as well as re-representing existing tree models (given as polygons).

We present a method for structural summarization and abstraction of complex spatial arrangements found in architectural drawings. The method is based on the well-known Gestalt rules, which summarize how forms, patterns, and semantics are perceived by humans from bits and pieces of geometric information. Although defining a computational model for each rule alone has been extensively studied, modeling a conjoint of Gestalt rules remains a challenge. In this work, we develop a computational framework which models Gestalt rules and more importantly, their complex interactions. We apply conjoining rules to line drawings, to detect groups of objects and repetitions that conform to Gestalt principles. We summarize and abstract such groups in ways that maintain structural semantics by displaying only a reduced number of repeated elements, or by replacing them with simpler shapes. We show an application of our method to line drawings of architectural models of various styles, and the potential of extending the technique to other computer-generated illustrations, and three-dimensional models.

We introduce an algorithm for unsupervised co-segmentation of a set of shapes so as to reveal the semantic shape parts and establish their correspondence across the set. The input set may exhibit significant shape variability where the shapes do not admit proper spatial alignment and the corresponding parts in any pair of shapes may be geometrically dissimilar. Our algorithm can handle such challenging input sets since, first, we perform co-analysis in a descriptor space , where a combination of shape descriptors relates the parts independently of their pose, location, and cardinality. Secondly, we exploit a key enabling feature of the input set, namely, dissimilar parts may be "linked" through third-parties present in the set. The links are derived from the pairwise similarities between the parts' descriptors. To reveal such linkages, which may manifest themselves as anisotropic and non-linear structures in the descriptor space, we perform spectral clustering with the aid of diffusion maps. We show that with our approach, we are able to co-segment sets of shapes that possess significant variability, achieving results that are close to those of a supervised approach.

A 3D burr puzzle is a 3D model that consists of interlocking pieces with a single-key property. That is, when the puzzle is assembled, all the pieces are notched except one single key component which remains mobile. The intriguing property of the assembled burr puzzle is that it is stable, perfectly interlocked, without glue or screws, etc. Moreover, a burr puzzle consisting of a small number of pieces is still rather difficult to solve since the assembly must follow certain orders while the combinatorial complexity of the puzzle's piece arrangements is extremely high. In this paper, we generalize the 6-piece orthogonal burr puzzle (a knot) to design and model burr puzzles from 3D models. Given a 3D input model, we first interactively embed a network of knots into the 3D shape. Our method automatically optimizes and arranges the orientation of each knot, and modifies pieces of adjacent knots with an appropriate connection type. Then, following the geometry of the embedded pieces, the entire 3D model is partitioned by splitting the solid while respecting the assembly motion of embedded pieces. The main technical challenge is to enforce the single-key property and ensure the assembly/disassembly remains feasible, as the puzzle pieces in a network of knots are highly interlocked. Lastly, we also present an automated approach to generate the visualizations of the puzzle assembly process.

We introduce an algorithm for 3D object modeling where the user draws creative inspiration from an object captured in a single photograph. Our method leverages the rich source of photographs for creative 3D modeling. However, with only a photo as a guide, creating a 3D model from scratch is a daunting task. We support the modeling process by utilizing an available set of 3D candidate models. Specifically, the user creates a digital 3D model as a geometric variation from a 3D candidate. Our modeling technique consists of two major steps. The first step is a user-guided image-space object segmentation to reveal the structure of the photographed object. The core step is the second one, in which a 3D candidate is automatically deformed to fit the photographed target under the guidance of silhouette correspondence. The set of candidate models have been pre-analyzed to possess useful high-level structural information, which is heavily utilized in both steps to compensate for the ill-posedness of the analysis and modeling problems based only on content in a single image. Equally important, the structural information is preserved by the geometric variation so that the final product is coherent with its inherited structural information readily usable for subsequent model refinement or processing.

Abstract Automatic camera control for scenes depicting human motion is an imperative topic in motion capture base animation, computer games, and other animation based fields. This challenging control problem is complex and combines both geometric constraints, visibility requirements, and aesthetic elements. Therefore, existing optimization‐based approaches for human action overview are often too demanding for online computation. In this paper, we introduce an effective automatic camera control which is extremely efficient and allows online performance. Rather than optimizing a complex quality measurement, at each time it selects one active camera from a multitude of cameras that render the dynamic scene. The selection is based on the correlation between each view stream and the human motion in the scene. Two factors allow for rapid selection among tens of candidate views in real‐time, even for complex multi‐character scenes: the efficient rendering of the multitude of view streams, and optimized calculations of the correlations using modified CCA. In addition to the method's simplicity and speed, it exhibits good agreement with both cinematic idioms and previous human motion camera control work. Our evaluations show that the method is able to cope with the challenges put forth by severe occlusions, multiple characters and complex scenes.

Abstract This paper challenges the difficult problem of automatic semantic correspondence between two given shapes which are semantically similar but possibly geometrically very different (e.g., a dog and an elephant). We argue that the challenging part is the establishment of a sparse correspondence and show that it can be efficiently solved by considering the underlying skeletons augmented with intrinsic surface information. To avoid potentially costly direct search for the best combinatorial match between two sets of skeletal feature nodes, we introduce a statistical correspondence algorithm based on a novel voting scheme, which we call electors voting. The electors are a rather large set of correspondences which then vote to synthesize the final correspondence. The electors are selected via a combinatorial search with pruning tests designed to quickly filter out a vast majority of bad correspondence. This voting scheme is both efficient and insensitive to parameter and threshold settings. The effectiveness of the method is validated by precision‐recall statistics with respect to manually defined ground truth. We show that high quality correspondences can be instantaneously established for a wide variety of model pairs, which may have different poses, surface details, and only partial semantic correspondence.

Abstract We present an automatic method to recover high‐resolution texture over an object by mapping detailed photographs onto its surface. Such high‐resolution detail often reveals inaccuracies in geometry and registration, as well as lighting variations and surface reflections. Simple image projection results in visible seams on the surface. We minimize such seams using a global optimization that assigns compatible texture to adjacent triangles. The key idea is to search not only combinatorially over the source images, but also over a set of local image transformations that compensate for geometric misalignment. This broad search space is traversed using a discrete labeling algorithm, aided by a coarse‐to‐fine strategy. Our approach significantly improves resilience to acquisition errors, thereby allowing simple and easy creation of textured models for use in computer graphics.

Abstract Many times, even if a crowd simulation looks good in general, there could be some specific individual behaviors which do not seem correct. Spotting such problems manually can become tedious, but ignoring them may harm the simulation's credibility. In this paper we present a data‐driven approach for evaluating the behaviors of individuals within a simulated crowd. Based on video‐footage of a real crowd, a database of behavior examples is generated. Given a simulation of a crowd, an analog analysis is performed on it, defining a set of queries, which are matched by a similarity function to the database examples. The results offer a possible objective answer to the question of how similar are the simulated individual behaviors to real observed behaviors. Moreover, by changing the video input one can change the context of evaluation. We show several examples of evaluating simulated crowds produced using different techniques and comprising of dense crowds, sparse crowds and flocks.

Abstract Aesthetic images evoke an emotional response that transcends mere visual appreciation. In this work we develop a novel computational means for evaluating the composition aesthetics of a given image based on measuring several well‐grounded composition guidelines. A compound operator of crop‐and‐retarget is employed to change the relative position of salient regions in the image and thus to modify the composition aesthetics of the image. We propose an optimization method for automatically producing a maximally‐aesthetic version of the input image. We validate the performance of the method and show its effectiveness in a variety of experiments.

Abstract We introduce the notion of consensus skeletons for non‐rigid space‐time registration of a deforming shape. Instead of basing the registration on point features, which are local and sensitive to noise, we adopt the curve skeleton of the shape as a global and descriptive feature for the task. Our method uses no template and only assumes that the skeletal structure of the captured shape remains largely consistent over time. Such an assumption is generally weaker than those relying on large overlap of point features between successive frames, allowing for more sparse acquisition across time. Building our registration framework on top of the low‐dimensional skeleton‐time structure avoids heavy processing of dense point or volumetric data, while skeleton consensusization provides robust handling of incompatibilities between per‐frame skeletons. To register point clouds from all frames, we deform them by their skeletons, mirroring the skeleton registration process, to jump‐start a non‐rigid ICP. We present results for non‐rigid space‐time registration under sparse and noisy spatio‐temporal sampling, including cases where data was captured from only a single view.

We introduce an ℓ 1 -sparse method for the reconstruction of a piecewise smooth point set surface. The technique is motivated by recent advancements in sparse signal reconstruction. The assumption underlying our work is that common objects, even geometrically complex ones, can typically be characterized by a rather small number of features. This, in turn, naturally lends itself to incorporating the powerful notion of sparsity into the model. The sparse reconstruction principle gives rise to a reconstructed point set surface that consists mainly of smooth modes, with the residual of the objective function strongly concentrated near sharp features. Our technique is capable of recovering orientation and positions of highly noisy point sets. The global nature of the optimization yields a sparse solution and avoids local minima. Using an interior-point log-barrier solver with a customized preconditioning scheme, the solver for the corresponding convex optimization problem is competitive and the results are of high quality.

Camouflage images contain one or more hidden figures that remain imperceptible or unnoticed for a while. In one possible explanation, the ability to delay the perception of the hidden figures is attributed to the theory that human perception works in two main phases: feature search and conjunction search. Effective camouflage images make feature based recognition difficult, and thus force the recognition process to employ conjunction search, which takes considerable effort and time. In this paper, we present a technique for creating camouflage images. To foil the feature search, we remove the original subtle texture details of the hidden figures and replace them by that of the surrounding apparent image. To leave an appropriate degree of clues for the conjunction search, we compute and assign new tones to regions in the embedded figures by performing an optimization between two conflicting terms, which we call immersion and standout , corresponding to hiding and leaving clues, respectively. We show a large number of camouflage images generated by our technique, with or without user guidance. We have tested the quality of the images in an extensive user study, showing a good control of the difficulty levels.

This paper introduces a method for optimizing the tiles of a quad-mesh. Given a quad-based surface, the goal is to generate a set of K quads whose instances can produce a tiled surface that approximates the input surface. A solution to the problem is a K-set tilable surface, which can lead to an effective cost reduction in the physical construction of the given surface. Rather than molding lots of different building blocks, a K-set tilable surface requires the construction of K prefabricated components only. To realize the K-set tilable surface, we use a cluster-optimize approach. First, we iteratively cluster and analyze: clusters of similar shapes are merged, while edge connections between the K quads on the target surface are analyzed to learn the induced flexibility of the K-set tilable surface. Then, we apply a non-linear optimization model with constraints that maintain the K quads connections and shapes, and show how quad-based surfaces are optimized into K-set tilable surfaces. Our algorithm is demonstrated on various surfaces, including some that mimic the exteriors of certain renowned building landmarks.

We introduce an interactive tool which enables a user to quickly assemble an architectural model directly over a 3D point cloud acquired from large-scale scanning of an urban scene. The user loosely defines and manipulates simple building blocks, which we call SmartBoxes, over the point samples. These boxes quickly snap to their proper locations to conform to common architectural structures. The key idea is that the building blocks are smart in the sense that their locations and sizes are automatically adjusted on-the-fly to fit well to the point data, while at the same time respecting contextual relations with nearby similar blocks. SmartBoxes are assembled through a discrete optimization to balance between two snapping forces defined respectively by a data-fitting term and a contextual term, which together assist the user in reconstructing the architectural model from a sparse and noisy point cloud. We show that a combination of the user's interactive guidance and high-level knowledge about the semantics of the underlying model, together with the snapping forces, allows the reconstruction of structures which are partially or even completely missing from the input.

We present cone carving, a novel space carving technique supporting topologically correct surface reconstruction from an incomplete scanned point cloud. The technique utilizes the point samples not only for local surface position estimation but also to obtain global visibility information under the assumption that each acquired point is visible from a point lying outside the shape. This enables associating each point with a generalized cone, called the visibility cone , that carves a portion of the outside ambient space of the shape from the inside out. These cones collectively provide a means to better approximate the signed distances to the shape specifically near regions containing large holes in the scan, allowing one to infer the correct surface topology. Combining the new distance measure with conventional RBF, we define an implicit function whose zero level set defines the surface of the shape. We demonstrate the utility of cone carving in coping with significant missing data and raw scans from a commercial 3D scanner as well as synthetic input.

We perform co-analysis of a set of man-made 3D objects to allow the creation of novel instances derived from the set. We analyze the objects at the part level and treat the anisotropic part scales as a shape style. The co-analysis then allows style transfer to synthesize new objects. The key to co-analysis is part correspondence, where a major challenge is the handling of large style variations and diverse geometric content in the shape set. We propose style-content separation as a means to address this challenge. Specifically, we define a correspondence-free style signature for style clustering. We show that confining analysis to within a style cluster facilitates tasks such as co-segmentation, content classification, and deformation-driven part correspondence. With part correspondence between each pair of shapes in the set, style transfer can be easily performed. We demonstrate our analysis and synthesis results on several sets of man-made objects with style and content variations.

Recent advances in scanning technologies, in particular devices that extract depth through active sensing, allow fast scanning of urban scenes. Such rapid acquisition incurs imperfections: large regions remain missing, significant variation in sampling density is common, and the data is often corrupted with noise and outliers. However, buildings often exhibit large scale repetitions and self-similarities. Detecting, extracting, and utilizing such large scale repetitions provide powerful means to consolidate the imperfect data. Our key observation is that the same geometry, when scanned multiple times over reoccurrences of instances, allow application of a simple yet effective non-local filtering. The multiplicity of the geometry is fused together and projected to abase-geometrydefined by clustering corresponding surfaces. Denoising is applied by separating the process into off-plane and in-plane phases. We show that the consolidation of the reoccurrences provides robust denoising and allow reliable completion of missing parts. We present evaluation results of the algorithm on several LiDAR scans of buildings of varying complexity and styles.

We present an easy-to-use image retouching technique for realistic reshaping of human bodies in a single image. A model-based approach is taken by integrating a 3D whole-body morphable model into the reshaping process to achieve globally consistent editing effects. A novel body-aware image warping approach is introduced to reliably transfer the reshaping effects from the model to the image, even under moderate fitting errors. Thanks to the parametric nature of the model, our technique parameterizes the degree of reshaping by a small set of semantic attributes, such as weight and height. It allows easy creation of desired reshaping effects by changing the full-body attributes, while producing visually pleasing results even for loosely-dressed humans in casual photographs with a variety of poses and shapes.

Summary form only given. In my talk I will present some surface reconstruction techniques that handle imperfect data. Such data is common in raw scans and contains large missing parts, ghost outliers and under-sampled regions. We explore reconstruction techniques that focus on such problematic regions. Our general goal is recovering the expected shape in terms of global topology and local geometric detail. I will present different methods that focus on several essential problems of imperfect data reconstruction: In the first part I will present a deformable model method that recovers a watertight surface and well interprets the topology of imperfect scans. Then, I will briefly introduce an interactive topology-aware reconstruction method that uses minimal user input to correctly reconstruct regions where the topology of the model cannot be automatically induced. I will also show how the reconstruction can be improved with the use of local priors and a visibility prior. Then, I will present a registration technique that handle noisy data. The technique allows registering raw noisy data, possibly contaminated with outliers, without pre-filtering or denoising the data. Finally, if time permits, I will present a novel approach based on the argument that man-made models can be distilled using a few special 1D wires and their mutual relations. Maintaining the properties of such a small number of wires allows preserving the defining characteristics of the entire object. The new method takes an analyze-and-edit approach, where prior to editing, it performs a light-weight analysis of the input shape to extract a descriptive set of wires. Analyzing the individual and mutual properties of the wires, and augmenting them with geometric attributes makes them intelligent and ready to be manipulated. Editing the object by modifying the intelligent wires leads to a powerful editing framework that retains the original design intent and object characteristics.

We introduce principal-channels for cutting out objects from an image by one-sided scribbles. We demonstrate that few scribbles, all from within the object of interest, are sufficient to mark it out. One-sided scribbles provide significantly less information than two-sided ones. Thus, it is required to maximize the use of image-information. Our approach is to first analyze the image with a large filter bank and generate a high-dimensional feature space. We then extract a set of principal-channels that discern one object from another. We show that by applying an iterative graph-cut optimization over the principal-channels, we can cut out the object of interest.

We present a semi-automatic system that converts conventional video shots to stereoscopic video pairs. The system requires just a few user-scribbles in a sparse set of frames. The system combines a diffusion scheme, which takes into account the local saliency and the local motion at each video location, coupled with a classification scheme that assigns depth to image patches. The system tolerates both scene motion and camera motion. In typical shots, containing hundreds of frames, even in the face of significant motion, it is enough to mark scribbles on the first and last frames of the shot. Once marked, plausible stereo results are obtained in a matter of seconds, leading to a scalable video conversion system. Finally, we validate our results with ground truth stereo video.

Abstract Displaying panoramic and wide angle views on a flat 2D display surface is necessarily prone to distortions. Perspective projections are limited to fairly narrow view angles. Cylindrical and spherical projections can show full 360° panoramas, but at the cost of curving straight lines, interfering with the perception of salient shapes in the scene. In this paper, we introducelocally‐adapted projections. Such projections are defined by a continuous projection surface consisting of both near‐planar and curved parts. A simple and intuitive user interface allows the specification of regions of interest to be mapped to the near‐planar parts, thereby reducing bending artifacts. We demonstrate the effectiveness of our approach on a variety of panoramic and wide angle images, including both indoor and outdoor scenes.

Abstract The notion of parts in a shape plays an important role in many geometry problems, including segmentation, correspondence, recognition, editing, and animation. As the fundamental geometric representation of 3D objects in computer graphics is surface‐based, solutions of many such problems utilize a surface metric, a distance function defined over pairs of points on the surface, to assist shape analysis and understanding. The main contribution of our work is to bring together these two fundamental concepts: shape parts and surface metric. Specifically, we develop a surface metric that is part‐aware. To encode part information at a point on a shape, we model its volumetric context – called the volumetric shape image (VSI) – inside the shape's enclosed volume, to capture relevant visibility information. We then define the part‐aware metric by combining an appropriate VSI distance with geodesic distance and normal variation. We show how the volumetric view on part separation addresses certain limitations of the surface view, which relies on concavity measures over a surface as implied by the well‐known minima rule. We demonstrate how the new metric can be effectively utilized in various applications including mesh segmentation, shape registration, part‐aware sampling and shape retrieval.

Abstract Changing the appearance of an image can be a complex and non‐intuitive task. Many times the target image colors and look are only known vaguely and many trials are needed to reach the desired results. Moreover, the effect of a specific change on an image is difficult to envision, since one must take into account spatial image considerations along with the color constraints. Tools provided today by image processing applications can become highly technical and non‐intuitive including various gauges and knobs. In this paper we introduce a method for changing image appearance by navigation, focusing on recoloring images. The user visually navigates a high dimensional space of possible color manipulations of an image. He can either explore in it for inspiration or refine his choices by navigating into sub regions of this space to a specific goal. This navigation is enabled by modeling the chroma channels of an image's colors using a Gaussian Mixture Model (GMM). The Gaussians model both color and spatial image coordinates, and provide a high dimensional parameterization space of a rich variety of color manipulations. The user's actions are translated into transformations of the parameters of the model, which recolor the image. This approach provides both inspiration and intuitive navigation in the complex space of image color manipulations.

Seamless cloning of a source image patch into a target image is an important and useful image editing operation, which has received considerable research attention in recent years. This operation is typically carried out by solving a Poisson equation with Dirichlet boundary conditions, which smoothly interpolates the discrepancies between the boundary of the source patch and the target across the entire cloned area. In this paper we introduce an alternative, coordinate-based approach, where rather than solving a large linear system to perform the aforementioned interpolation, the value of the interpolant at each interior pixel is given by a weighted combination of values along the boundary. More specifically, our approach is based on Mean-Value Coordinates (MVC). The use of coordinates is advantageous in terms of speed, ease of implementation, small memory footprint, and parallelizability, enabling real-time cloning of large regions, and interactive cloning of video streams. We demonstrate a number of applications and extensions of the coordinate-based framework.

Man-made objects are largely dominated by a few typical features that carry special characteristics and engineered meanings. State-of-the-art deformation tools fall short at preserving such characteristic features and global structure. We introduce iWIRES, a novel approach based on the argument that man-made models can be distilled using a few special 1D wires and their mutual relations. We hypothesize that maintaining the properties of such a small number of wires allows preserving the defining characteristics of the entire object. We introduce an analyze-and-edit approach, where prior to editing, we perform a light-weight analysis of the input shape to extract a descriptive set of wires. Analyzing the individual and mutual properties of the wires, and augmenting them with geometric attributes makes them intelligent and ready to be manipulated. Editing the object by modifying the intelligent wires leads to a powerful editing framework that retains the original design intent and object characteristics. We show numerous results of manipulation of man-made shapes using our editing technique.

We consolidate an unorganized point cloud with noise, outliers, non-uniformities, and in particular interference between close-by surface sheets as a preprocess to surface generation, focusing on reliable normal estimation. Our algorithm includes two new developments. First, a weighted locally optimal projection operator produces a set of denoised, outlier-free and evenly distributed particles over the original dense point cloud, so as to improve the reliability of local PCA for initial estimate of normals. Next, an iterative framework for robust normal estimation is introduced, where a priority-driven normal propagation scheme based on a new priority measure and an orientation-aware PCA work complementarily and iteratively to consolidate particle normals. The priority setting is reinforced with front stopping at thin surface features and normal flipping to enable robust handling of the close-by surface sheet problem. We demonstrate how a point cloud that is well-consolidated by our method steers conventional surface generation schemes towards a proper interpretation of the input data.

Emergence refers to the unique human ability to aggregate information from seemingly meaningless pieces, and to perceive a whole that is meaningful. This special skill of humans can constitute an effective scheme to tell humans and machines apart. This paper presents a synthesis technique to generate images of 3D objects that are detectable by humans, but difficult for an automatic algorithm to recognize. The technique allows generating an infinite number of images with emerging figures. Our algorithm is designed so that locally the synthesized images divulge little useful information or cues to assist any segmentation or recognition procedure. Therefore, as we demonstrate, computer vision algorithms are incapable of effectively processing such images. However, when a human observer is presented with an emergence image, synthesized using an object she is familiar with, the figure emerges when observed as a whole. We can control the difficulty level of perceiving the emergence effect through a limited set of parameters. A procedure that synthesizes emergence images can be an effective tool for exploring and understanding the factors affecting computer vision techniques.

Many inhomogeneous real-world textures are non-stationary and exhibit various large scale patterns that are easily perceived by a human observer. Such textures violate the assumptions underlying most state-of-the-art example-based synthesis methods. Consequently, they cannot be properly reproduced by these methods, unless a suitable control map is provided to guide the synthesis process. Such control maps are typically either user specified or generated by a simulation. In this paper, we present an alternative: a method for automatic example-based generation of control maps, geared at synthesis of natural, highly inhomogeneous textures, such as those resulting from natural aging or weathering processes. Our method is based on the observation that an appropriate control map for many of these textures may be modeled as a superposition of several layers, where the visible parts of each layer are occupied by a more homogeneous texture. Thus, given a decomposition of a texture exemplar into a small number of such layers, we employ a novel example-based shape synthesis algorithm to automatically generate a new set of layers. Our shape synthesis algorithm is designed to preserve both local and global characteristics of the exemplar's layer map. This process results in a new control map, which then may be used to guide the subsequent texture synthesis process.

We present an algorithm for curve skeleton extraction from imperfect point clouds where large portions of the data may be missing. Our construction is primarily based on a novel notion of generalized rotational symmetry axis (ROSA) of an oriented point set. Specifically, given a subset S of oriented points, we introduce a variational definition for an oriented point that is most rotationally symmetric with respect to S . Our formulation effectively utilizes normal information to compensate for the missing data and leads to robust curve skeleton computation over regions of a shape that are generally cylindrical. We present an iterative algorithm via planar cuts to compute the ROSA of a point cloud. This is complemented by special handling of non-cylindrical joint regions to obtain a centered, topologically clean, and complete 1D skeleton. We demonstrate that quality curve skeletons can be extracted from a variety of shapes captured by incomplete point clouds. Finally, we show how our algorithm assists in shape completion under these challenges by developing a skeleton-driven point cloud completion scheme.

The essence of a 3D shape can often be well captured by its salient feature curves. In this paper, we explore the use of salient curves in synthesizing intuitive, shape-revealing textures on surfaces. Our texture synthesis is guided by two principles: matching the direction of the texture patterns to those of the salient curves, and aligning the prominent feature lines in the texture to the salient curves exactly. We have observed that textures synthesized by these principles not only fit naturally to the surface geometry, but also visually reveal, even reinforce, the shape's essential characteristics. We call these feature-aligned shape texturing . Our technique is fully automatic, and introduces two novel technical components in vector-field-guided texture synthesis: an algorithm that orients the salient curves on a surface for constrained vector field generation, and a feature-to-feature texture optimization.

Boundary snapping is an interactive image cutout algorithm that requires a small number of user supplied control points, or landmarks, to infer the cutout contour. The key idea is to match the appearance of all points along the desired contour to the landmark points, where appearance is given by an intensity profile perpendicular to the boundary. An optimization process attempts to find a contour that maximizes the similarity score of its points with the landmarks. This approach works well in the typical case where the foreground and background differ in appearance, as well as in challenging cases where the subject is clearly perceived, but the regions on both sides of the boundary are similar and cannot be easily discriminated. By enabling the user to define the boundary points directly, the technique is not limited to boundaries that necessarily have to be the most salient or high gradient feature in the region. It can also be used for margin cutout around the boundary. The use of multiple control points along the boundary can handle spatially varying attributes as both foreground and background may change in appearance along the boundary. The final result is accurate, because it allows the user to enforce hard constraints on the boundary directly, at the expense of moderate user labor in positioning the landmark points. Finally, the algorithm is fast, works on a variety of images, and handles situations where the boundary is not obvious.

Abstract Non‐rigid 3D shape correspondence is a fundamental and difficult problem. Most applications which require a correspondence rely on manually selected markers. Without user assistance, the performances of existing automatic correspondence methods depend strongly on a good initial shape alignment or shape prior, and they generally do not tolerate large shape variations. We present an automatic feature correspondence algorithm capable of handling large, non‐rigid shape variations, as well as partial matching. This is made possible by leveraging the power of state‐of‐the‐art mesh deformation techniques and relying on a combinatorial tree traversal for correspondence search. The search is deformation‐driven, prioritized by a self‐distortion energy measured on meshes deformed according to a given correspondence. We demonstrate the ability of our approach to naturally match shapes which differ in pose, local scale, part decomposition, and geometric detail through numerous examples.

We introduce 4PCS, a fast and robust alignment scheme for 3D point sets that uses wide bases, which are known to be resilient to noise and outliers. The algorithm allows registering raw noisy data, possibly contaminated with outliers, without pre-filtering or denoising the data. Further, the method significantly reduces the number of trials required to establish a reliable registration between the underlying surfaces in the presence of noise, without any assumptions about starting alignment. Our method is based on a novel technique to extract all coplanar 4-points sets from a 3D point set that are approximately congruent, under rigid transformation, to a given set of coplanar 4-points. This extraction procedure runs in roughly O(n 2 + k) time, where n is the number of candidate points and k is the number of reported 4-points sets. In practice, when noise level is low and there is sufficient overlap, using local descriptors the time complexity reduces to O(n + k) . We also propose an extension to handle similarity and affine transforms. Our technique achieves an order of magnitude asymptotic acceleration compared to common randomized alignment techniques. We demonstrate the robustness of our algorithm on several sets of multiple range scans with varying degree of noise, outliers, and extent of overlap.

During the last decade, motion capture data has emerged and gained a leading role in animations, games and 3D environments. Many of these applications require the creation of expressive overview video clips capturing the human motion, however sufficient attention has not been given to this problem. In this paper, we present a technique that generates an overview video based on the analysis of motion capture data. Our method is targeted for applications of 3D character based animations, automating, for example, the action summary and gameplay overview in simulations and computer games. We base our method on quantum annealing optimization with an objective function that respects the analysis of the character motion and the camera movement constraints. It automatically generates a smooth camera control path, splitting it to several shots if required. To evaluate our method, we introduce a novel camera placement metric which is evaluated against previous work and conduct a user study comparing our results with the various systems.

Extraction of curve-skeletons is a fundamental problem with many applications in computer graphics and visualization. In this paper, we present a simple and robust skeleton extraction method based on mesh contraction. The method works directly on the mesh domain, without pre-sampling the mesh model into a volumetric representation. The method first contracts the mesh geometry into zero-volume skeletal shape by applying implicit Laplacian smoothing with global positional constraints. The contraction does not alter the mesh connectivity and retains the key features of the original mesh. The contracted mesh is then converted into a 1D curve-skeleton through a connectivity surgery process to remove all the collapsed faces while preserving the shape of the contracted mesh and the original topology. The centeredness of the skeleton is refined by exploiting the induced skeleton-mesh mapping. In addition to producing a curve skeleton, the method generates other valuable information about the object's geometry, in particular, the skeleton-vertex correspondence and the local thickness, which are useful for various applications. We demonstrate its effectiveness in mesh segmentation and skinning animation.

Humans usually associate an upright orientation with objects, placing them in a way that they are most commonly seen in our surroundings. While it is an open challenge to recover the functionality of a shape from its geometry alone, this paper shows that it is often possible to infer its upright orientation by analyzing its geometry. Our key idea is to reduce the two-dimensional (spherical) orientation space to a small set of orientation candidates using functionality-related geometric properties of the object, and then determine the best orientation using an assessment function of several functional geometric attributes defined with respect to each candidate. Specifically we focus on obtaining the upright orientation for man-made objects that typically stand on some flat surface (ground, floor, table, etc.), which include the vast majority of objects in our everyday surroundings. For these types of models orientation candidates can be defined according to static equilibrium. For each candidate, we introduce a set of discriminative attributes linking shape to function. We learn an assessment function of these attributes from a training set using a combination of Random Forest classifier and Support Vector Machine classifier. Experiments demonstrate that our method generalizes well and achieves about 90% prediction accuracy for both a 10-fold cross-validation over the training set and a validation with an independent test set.

Character skinning determines how the shape of the surface geometry changes as a function of the pose of the underlying skeleton. In this paper we describe skinning templates, which define common deformation behaviors for common joint types. This abstraction allows skinning solutions to be shared and reused, and they allow a user to quickly explore many possible alternatives for the skinning behavior of a character. The skinning templates are implemented using cage-based deformations, which offer a flexible design space within which to develop reusable skinning behaviors. We demonstrate the interactive use of skinning templates to quickly explore alternate skinning behaviors for 3D models.

In this paper, we introduce a novel system for browsing, enhancing, and manipulating casual outdoor photographs by combining them with already existing georeferenced digital terrain and urban models. A simple interactive registration process is used to align a photograph with such a model. Once the photograph and the model have been registered, an abundance of information, such as depth, texture, and GIS data, becomes immediately available to our system. This information, in turn, enables a variety of operations, ranging from dehazing and relighting the photograph, to novel view synthesis, and overlaying with geographic information. We describe the implementation of a number of these applications and discuss possible extensions. Our results show that augmenting photographs with already available 3D models of the world supports a wide variety of new ways for us to experience and interact with our everyday snapshots.

Resizing of 3D models can be very useful when creating new models or placing models inside different scenes. However, uniform scaling is limited in its applicability while straightforward non-uniform scaling can destroy features and lead to serious visual artifacts. Our goal is to define a method that protects model features and structures during resizing. We observe that typically, during scaling some parts of the models are more vulnerable than others, undergoing undesirable deformation. We automatically detect vulnerable regions and carry this information to a protective grid defined around the object, defining a vulnerability map. The 3D model is then resized by a space-deformation technique which scales the grid non-homogeneously while respecting this map. Using space-deformation allows processing of common models of man-made objects that consist of multiple components and contain non-manifold structures. We show that our technique resizes models while suppressing undesirable distortion, creating models that preserve the structure and features of the original ones.

When human raters are presented with a collection of shapes and asked to rank them according to their aesthetic appeal, the results often indicate that there is a statistical consensus among the raters. Yet it might be difficult to define a succinct set of rules that capture the aesthetic preferences of the raters. In this work, we explore a data-driven approach to aesthetic enhancement of such shapes. Specifically, we focus on the challenging problem of enhancing the aesthetic appeal (or the attractiveness ) of human faces in frontal photographs (portraits), while maintaining close similarity with the original. The key component in our approach is an automatic facial attractiveness engine trained on datasets of faces with accompanying facial attractiveness ratings collected from groups of human raters. Given a new face, we extract a set of distances between a variety of facial feature locations, which define a point in a high-dimensional "face space". We then search the face space for a nearby point with a higher predicted attractiveness rating. Once such a point is found, the corresponding facial distances are embedded in the plane and serve as a target to define a 2D warp field which maps the original facial features to their adjusted locations. The effectiveness of our technique was experimentally validated by independent rating experiments, which indicate that it is indeed capable of increasing the facial attractiveness of most portraits that we have experimented with.

We introduce Green Coordinates for closed polyhedral cages. The coordinates are motivated by Green's third integral identity and respect both the vertices position and faces orientation of the cage. We show that Green Coordinates lead to space deformations with a shape-preserving property. In particular, in 2D they induce conformal mappings, and extend naturally to quasi-conformal mappings in 3D. In both cases we derive closed-form expressions for the coordinates, yielding a simple and fast algorithm for cage-based space deformation. We compare the performance of Green Coordinates with those of Mean Value Coordinates and Harmonic Coordinates and show that the advantage of the shape-preserving property is not achieved at the expense of speed or simplicity. We also show that the new coordinates extend the mapping in a natural analytic manner to the exterior of the cage, allowing the employment of partial cages.

This paper presents an optimization-based halftoning technique that preserves the structure and tone similarities between the original and the halftone images. By optimizing an objective function consisting of both the structure and the tone metrics, the generated halftone images preserve visually sensitive texture details as well as the local tone. It possesses the blue-noise property and does not introduce annoying patterns. Unlike the existing edge-enhancement halftoning, the proposed method does not suffer from the deficiencies of edge detector. Our method is tested on various types of images. In multiple experiments and the user study, our method consistently obtains the best scores among all tested methods.

We introduce a volumetric space-time technique for the reconstruction of moving and deforming objects from point data. The output of our method is a four-dimensional space-time solid, made up of spatial slices, each of which is a three-dimensional solid bounded by a watertight manifold. The motion of the object is described as an incompressible flow of material through time. We optimize the flow so that the distance material moves from one time frame to the next is bounded, the density of material remains constant, and the object remains compact. This formulation overcomes deficiencies in the acquired data, such as persistent occlusions, errors, and missing frames. We demonstrate the performance of our flow-based technique by reconstructing coherent sequences of watertight models from incomplete scanner data.

Video retargeting is the process of transforming an existing video to fit the dimensions of an arbitrary display. A compelling retargeting aims at preserving the viewers' experience by maintaining the information content of important regions in the frame, whilst keeping their aspect ratio. An efficient algorithm for video retargeting is introduced. It consists of two stages. First, the frame is analyzed to detect the importance of each region in the frame. Then, a transformation that respects the analysis shrinks less important regions more than important ones. Our analysis is fully automatic and based on local saliency, motion detection and object detectors. The performance of the proposed algorithm is demonstrated on a variety of video sequences, and compared to the state of the art in image retargeting.

Handle-based mesh deformation is essentially a nonlinear problem. To allow scalability, the original deformation problem can be approximately represented by a compact set of control variables. We show the direct relation between the locations of handles on the mesh and the local rigidity under deformation, and introduce the notion of handle-aware rigidity . Then, we present a reduced model whose control variables are intelligently distributed across the surface, respecting the rigidity information and the geometry. Specifically, for each handle, the control variables are the transformations of the isolines of a harmonic scalar field representing the deformation propagation from that handle. The isolines constitute a virtual skeletal structure similar to the bones in skinning deformation, thus correctly capturing the low-frequency shape deformation. To interpolate the transformations from the isolines to the original mesh, we design a method which is local, linear and geometry-dependent. This novel interpolation scheme and the transformation-based reduced domain allow each iteration of the nonlinear solver to be fully computed over the reduced domain. This makes the per-iteration cost dependent on only the number of isolines and enables compelling deformation of highly detailed shapes at interactive rates. In addition, we show how the handle-driven isolines provide an efficient means for deformation transfer without full shape correspondence.

We present a novel method for synthesizing solid textures from 2D texture exemplars. First, we extend 2D texture optimization techniques to synthesize 3D texture solids. Next, the non-parametric texture optimization approach is integrated with histogram matching, which forces the global statistics of the synthesized solid to match those of the exemplar. This improves the convergence of the synthesis process and enables using smaller neighborhoods. In addition to producing compelling texture mapped surfaces, our method also effectively models the material in the interior of solid objects. We also demonstrate that our method is well-suited for synthesizing textures with a large number of channels per texel.

We introduce a Locally Optimal Projection operator (LOP) for surface approximation from point-set data. The operator is parameterization free, in the sense that it does not rely on estimating a local normal, fitting a local plane, or using any other local parametric representation. Therefore, it can deal with noisy data which clutters the orientation of the points. The method performs well in cases of ambiguous orientation, e.g., if two folds of a surface lie near each other, and other cases of complex geometry in which methods based upon local plane fitting may fail. Although defined by a global minimization problem, the method is effectively local, and it provides a second order approximation to smooth surfaces. Hence allowing good surface approximation without using any explicit or implicit approximation space. Furthermore, we show that LOP is highly robust to noise and outliers and demonstrate its effectiveness by applying it to raw scanned data of complex shapes.

This article introduces a method for mesh editing that is aimed at preserving shape and volume. We present two new developments: The first is a minimization of a functional expressing a geometric distance measure between two isometric surfaces. The second is a local volume analysis linking the volume of an object to its surface curvature. Our method is based upon the moving frames representation of meshes. Applying a rotation field to the moving frames defines an isometry. Given rotational constraints, the mesh is deformed by an optimal isometry defined by minimizing the distance measure between original and deformed meshes. The resulting isometry nicely preserves the surface details, but when large rotations are applied, the volumetric behavior of the model may be unsatisfactory. Using the local volume analysis, we define a scalar field by which we scale the moving frames. Scaled and rotated moving frames restore volumetric properties of the original mesh, while properly maintaining the surface details. Our results show that even extreme deformations can be applied to meshes, with only minimal distortion of surface details and object volume.

The reconstruction of a complete watertight model from scan data is still a difficult process. In particular, since scanned data is often incomplete, the reconstruction of the expected shape is an ill-posed problem. Techniques that reconstruct poorly-sampled areas without any user intervention fail in many cases to faithfully reconstruct the topology of the model. The method that we introduce in this paper is topology-aware: it uses minimal user input to make correct decisions at regions where the topology of the model cannot be automatically induced with a reasonable degree of confidence. We first construct a continuous function over a three-dimensional domain. This function is constructed by minimizing a penalty function combining the data points, user constraints, and a regularization term. The optimization problem is formulated in a mesh-independent manner, and mapped onto a specific mesh using the finite-element method. The zero level-set of this function is a first approximation of the reconstructed surface. At complex under-sampled regions, the constraints might be insufficient. Hence, we analyze the local topological stability of the zero level-set to detect weak regions of the surface. These regions are suggested to the user for adding local inside/outside constraints by merely scribbling over a 2D tablet. Each new user constraint modifies the minimization problem, which is solved incrementally. The process is repeated, converging to a topology-stable reconstruction. Reconstructions of models acquired by a structured-light scanner with a small number of scribbles demonstrate the effectiveness of the method.

A 3D shape signature is a compact representation for some essence of a shape. Shape signatures are commonly utilized as a fast indexing mechanism for shape retrieval. Effective shape signatures capture some global geometric properties which are scale, translation, and rotation invariant. In this paper, we introduce an effective shape signature which is also pose-oblivious. This means that the signature is also insensitive to transformations which change the pose of a 3D shape such as skeletal articulations. Although some topology-based matching methods can be considered pose-oblivious as well, our new signature retains the simplicity and speed of signature indexing. Moreover, contrary to topology-based methods, the new signature is also insensitive to the topology change of the shape, allowing us to match similar shapes with different genus. Our shape signature is a 2D histogram which is a combination of the distribution of two scalar functions defined on the boundary surface of the 3D shape. The first is a definition of a novel function called the local-diameter function. This function measures the diameter of the 3D shape in the neighborhood of each vertex. The histogram of this function is an informative measure of the shape which is insensitive to pose changes. The second is the centricity function that measures the average geodesic distance from one vertex to all other vertices on the mesh. We evaluate and compare a number of methods for measuring the similarity between two signatures, and demonstrate the effectiveness of our pose-oblivious shape signature within a 3D search engine application for different databases containing hundreds of models.

This work presents a method for estimating human facial attractiveness, based on supervised learning techniques. Numerous facial features that describe facial geometry, color and texture, combined with an average human attractiveness score for each facial image, are used to train various predictors. Facial attractiveness ratings produced by the final predictor are found to be highly correlated with human ratings, markedly improving previous machine learning achievements. Simulated psychophysical experiments with virtually manipulated images reveal preferences in the machine's judgments which are remarkably similar to those of humans. These experiments shed new light on existing theories of facial attractiveness such as the averageness, smoothness and symmetry hypotheses. It is intriguing to find that a machine trained explicitly to capture an operational performance criteria such as attractiveness rating, implicitly captures basic human psychophysical biases characterizing the perception of facial attractiveness in general.

We present a method for inhomogeneous 2D texture mapping guided by a feature mask, that preserves some regions of the image, such as foreground objects or other prominent parts. The method is able to arbitrarily warp a given image while preserving the shape of its features by constraining their deformation to be a similarity transformation. In particular, our method allows global or local changes to the aspect ratio of the texture without causing undesirable shearing to the features. The algorithmic core of our method is a particular formulation of the Laplacian editing technique, suited to accommodate similarity constraints on parts of the domain. The method is useful in digital imaging, texture design and any other applications involving image warping, where parts of the image have high familiarity and should retain their shape after modification.

Abstract We present a deformable model to reconstruct a surface from a point cloud. The model is based on an explicit mesh representation composed of multiple competing evolving fronts. These fronts adapt to the local feature size of the target shape in a coarse–to–fine manner. Hence, they approach towards the finer (local) features of the target shape only after the reconstruction of the coarse (global) features has been completed. This conservative approach leads to a better control and interpretation of the reconstructed topology. The use of an explicit representation for the deformable model guarantees water‐tightness and simple tracking of topological events. Furthermore, the coarse–to–fine nature of reconstruction enables adaptive handling of non‐homogenous sample density, including robustness to missing data in defected areas. Categories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Digitizing and scanning. Keywords: surface reconstruction, deformable models

Abstract In this paper we revisit the cells‐and‐portals visibility methods, originally developed for the special case of architectural interiors. We define an effectiveness measure for a cells‐and‐portals partition, and introduce a two‐pass algorithm that computes a cells‐and‐portals partition. The algorithm uses a simple heuristic that strives to create small portals as a means for generating an effective partition. The input to the algorithm is a set of half edges in 2D that can be extracted from a complex polygonal model. The first pass of the algorithm creates an initial partition, which is then refined by the second pass. We show that our method creates a partition that is more effective than the common BSP partition, even when the latter is further refined with the application of our second pass. Our cells‐and‐portals algorithm is designed to deal with arbitrarily oriented walls. The algorithm also supports outdoor scenes, where the vertical walls of the buildings serve as occluders and portals are extended above the buildings. We show that the extended portals allow an output‐sensitive rendering of large urban scenes. While most visibility algorithms use graphics hardware in order to cull hidden regions of the model, we examine the usefulness of a hardware‐assisted portal test as opposed to the conventional software test. Finally, since our two‐pass method is fully automatic and local, it supports incremental changes of the model by locally recomputing and updating the partition. We call our method ‘Breaking the Walls’ since it breaks out of indoor scenes to outdoor scenes, and allows walls to be broken interactively, with an instant updating of the partition. Copyright © 2006 John Wiley & Sons, Ltd.

Harmonic colors are sets of colors that are aesthetically pleasing in terms of human visual perception. In this paper, we present a method that enhances the harmony among the colors of a given photograph or of a general image, while remaining faithful, as much as possible, to the original colors. Given a color image, our method finds the best harmonic scheme for the image colors. It then allows a graceful shifting of hue values so as to fit the harmonic scheme while considering spatial coherence among colors of neighboring pixels using an optimization technique. The results demonstrate that our method is capable of automatically enhancing the color "look-and-feel" of an ordinary image. In particular, we show the results of harmonizing the background image to accommodate the colors of a foreground image, or the foreground with respect to the background, in a cut-and-paste setting. Our color harmonization technique proves to be useful in adjusting the colors of an image composed of several parts taken from different sources.

This article introduces a method for partial matching of surfaces represented by triangular meshes. Our method matches surface regions that are numerically and topologically dissimilar, but approximately similar regions. We introduce novel local surface descriptors which efficiently represent the geometry of local regions of the surface. The descriptors are defined independently of the underlying triangulation, and form a compatible representation that allows matching of surfaces with different triangulations. To cope with the combinatorial complexity of partial matching of large meshes, we introduce the abstraction of salient geometric features and present a method to construct them. A salient geometric feature is a compound high-level feature of nontrivial local shapes. We show that a relatively small number of such salient geometric features characterizes the surface well for various similarity applications. Matching salient geometric features is based on indexing rotation-invariant features and a voting scheme accelerated by geometric hashing. We demonstrate the effectiveness of our method with a number of applications, such as computing self-similarity, alignments, and subparts similarity.

Well distributed point sets play an important role in a variety of computer graphics contexts, such as anti-aliasing, global illumination, halftoning, non-photorealistic rendering, point-based modeling and rendering, and geometry processing. In this paper, we introduce a novel technique for rapidly generating large point sets possessing a blue noise Fourier spectrum and high visual quality. Our technique generates non-periodic point sets, distributed over arbitrarily large areas. The local density of a point set may be prescribed by an arbitrary target density function, without any preset bound on the maximum density. Our technique is deterministic and tile-based; thus, any local portion of a potentially infinite point set may be consistently regenerated as needed. The memory footprint of the technique is constant, and the cost to generate any local portion of the point set is proportional to the integral over the target density in that area. These properties make our technique highly suitable for a variety of real-time interactive applications, some of which are demonstrated in the paper.Our technique utilizes a set of carefully constructed progressive and recursive blue noise Wang tiles. The use of Wang tiles enables the generation of infinite non-periodic tilings. The progressive point sets inside each tile are able to produce spatially varying point densities. Recursion allows our technique to adaptively subdivide tiles only where high density is required, and makes it possible to zoom into point sets by an arbitrary amount, while maintaining a constant apparent density.

Illustrating motion in still imagery for the purpose of summary, abstraction and motion description is important for a diverse spectrum of fields, ranging from arts to sciences. In this paper, we introduce a method that produces an action synopsis for presenting motion in still images. The method carefully selects key poses based on an analysis of a skeletal animation sequence, to facilitate expressing complex motions in a single image or a small number of concise views. Our approach is to embed the high-dimensional motion curve in a low-dimensional Euclidean space, where the main characteristics of the skeletal action are kept. The lower complexity of the embedded motion curve allows a simple iterative method which analyzes the curve and locates significant points, associated with the key poses of the original motion. We present methods for illustrating the selected poses in an image as a means to convey the action. We applied our methods to a variety of motions of human actions given either as 3D animation sequences or as video clips, and generated images that depict their synopsis.

This article presents an algebraic analysis of a mesh-compression technique called high-pass quantization [Sorkine et al. 2003]. In high-pass quantization, a rectangular matrix based on the mesh topological Laplacian is applied to the vectors of the Cartesian coordinates of a polygonal mesh. The resulting vectors, called δ-coordinates, are then quantized. The applied matrix is a function of the topology of the mesh and the indices of a small set of mesh vertices (anchors) but not of the location of the vertices. An approximation of the geometry can be reconstructed from the quantized δ-coordinates and the spatial locations of the anchors. In this article, we show how to algebraically bound the reconstruction error that this method generates. We show that the small singular value of the transformation matrix can be used to bound both the quantization error and the rounding error which is due to the use of floating-point arithmetic. Furthermore, we prove a bound on this singular value. The bound is a function of the topology of the mesh and of the selected anchors. We also propose a new anchor-selection algorithm, inspired by this bound. We show experimentally that the method is effective and that the computed upper bound on the error is not too pessimistic.

We introduce a robust moving least-squares technique for reconstructing a piecewise smooth surface from a potentially noisy point cloud. We use techniques from robust statistics to guide the creation of the neighborhoods used by the moving least squares (MLS) computation. This leads to a conceptually simple approach that provides a unified framework for not only dealing with noise, but also for enabling the modeling of surfaces with sharp features.Our technique is based on a new robust statistics method for outlier detection: the forward-search paradigm. Using this powerful technique, we locally classify regions of a point-set to multiple outlier-free smooth regions. This classification allows us to project points on a locally smooth region rather than a surface that is smooth everywhere, thus defining a piecewise smooth surface and increasing the numerical stability of the projection operator. Furthermore, by treating the points across the discontinuities as outliers, we are able to define sharp features. One of the nice features of our approach is that it automatically disregards outliers during the surface-fitting phase.

We introduce a rigid motion invariant mesh representation based on discrete forms defined on the mesh. The reconstruction of mesh geometry from this representation requires solving two sparse linear systems that arise from the discrete forms: the first system defines the relationship between local frames on the mesh, and the second encodes the position of the vertices via the local frames. The reconstructed geometry is unique up to a rigid transformation of the mesh. We define surface editing operations by placing user-defined constraints on the local frames and the vertex positions. These constraints are incorporated in the two linear reconstruction systems, and their solution produces a deformed surface geometry that preserves the local differential properties in the least-squares sense. Linear combination of shapes expressed with our representation enables linear shape interpolation that correctly handles rotations. We demonstrate the effectiveness of the new representation with various detail-preserving editing operators and shape morphing.

In this paper we present a method for the intuitive editing of surface meshes by means of view-dependent sketching. In most existing shape deformation work, editing is carried out by selecting and moving a handle , usually a set of vertices. Our system lets the user easily determine the handle, either by silhouette selection and cropping, or by sketching directly onto the surface. Subsequently, an edit is carried out by sketching a new, view-dependent handle position or by indirectly influencing differential properties along the sketch. Combined, these editing and handle metaphors greatly simplify otherwise complex shape modeling tasks.

We introduce a new class of shape approximation techniques for irregular triangular meshes. Our method approximates the geometry of the mesh using a linear combination of a small number of basis vectors. The basis vectors are functions of the mesh connectivity and of the mesh indices of a number of anchor vertices. There is a fundamental difference between the bases generated by our method and those generated by geometry-oblivious methods, such as Laplacian-based spectral methods. In the latter methods, the basis vectors are functions of the connectivity alone. The basis vectors of our method, in contrast, are geometry-aware since they depend on both the connectivity and on a binary tagging of vertices that are "geometrically important" in the given mesh (e.g., extrema). We show that, by defining the basis vectors to be the solutions of certain least-squares problems, the reconstruction problem reduces to solving a single sparse linear least-squares problem. We also show that this problem can be solved quickly using a state-of-the-art sparse-matrix factorization algorithm. We show how to select the anchor vertices to define a compact effective basis from which an approximated shape can be reconstructed. Furthermore, we develop an incremental update of the factorization of the least-squares system. This allows a progressive scheme where an initial approximation is incrementally refined by a stream of anchor points. We show that the incremental update and solving the factored system are fast enough to allow an online refinement of the mesh geometry.

Mesh partitioning and parts extraction have become key ingredients for many mesh manipulation applications both manual and automatic. In this paper, we present an intelligent scissoring operator for meshes which supports both automatic segmentation and manual cutting. Instead of segmenting the mesh by clustering, our approach concentrates on finding and defining the contours for cutting. This approach is based on the minima rule, which states that human perception usually divides a surface into parts along the contours of concave discontinuity of the tangent plane. The technique uses feature extraction to find such candidate feature contours. Subsequently, such a contour can be selected either automatically or manually, or the user may draw a 2D line to start the scissoring process. The given open contour is completed to form a loop around a specific part of the mesh, and this loop is used as the initial position of a 3D geometric snake. The snake moves by relaxation until it settles to define the final scissoring position. This process uses several fundamental geometric mesh attributes, such as curvature and centricity, and enables both automatic segmentation and an easy-to-use intelligent-scissoring operator.

One of the main challenges in editing a mesh is to retain the visual appearance of the surface after applying various modifications. In this paper we advocate the use of linear differential coordinates as means to preserve the high-frequency detail of the surface. The differential coordinates represent the details and are defined by a linear transformation of the mesh vertices. This allows the reconstruction of the edited surface by solving a linear system that satisfies the reconstruction of the local details in least squares sense. Since the differential coordinates are defined in a global coordinate system they are not rotation-invariant. To compensate for that, we rotate them to agree with the rotation of an approximated local frame. We show that the linear least squares system can be solved fast enough to guarantee interactive response time thanks to a precomputed factorization of the coefficient matrix. We demonstrate that our approach enables to edit complex detailed meshes while keeping the shape of the details in their natural orientation.

In this paper we introduce least-squares meshes: meshes with a prescribed connectivity that approximate a set of control points in a least-squares sense. The given mesh consists of a planar graph with arbitrary connectivity and a sparse set of control points with geometry. The geometry of the mesh is reconstructed by solving a sparse linear system. The linear system not only defines a surface that approximates the given control points, but it also distributes the vertices over the surface in a fair way. That is, each vertex lies as close as possible to the center of gravity of its immediate neighbors. The least-squares meshes (LS-meshes) are a visually smooth and fair approximation of the given control points. We show that the connectivity of the mesh contains geometric information that affects the shape of the reconstructed surface. Finally, we discuss the applicability of LS-meshes to approximation of given surfaces, smooth completion and mesh editing.

Rendering large and complex virtual environments in real time remains a challenge as the complexity of models keeps growing. Visibility techniques such as occlusion culling can effectively reduce the rendering depth complexity.In my talk I'll survey recent advances in visibility determination. I'll focus on conservative and aggressive techniques and show how these techniques can be combined effectively with level of details and image-based techniques. I'll show how these new techniques can be accelerated by modern graphics cards to achieve interactive rendering of extremely complex scenes.

Sampling complex, real-world geometry with range scanning devices almost always yields imperfect surface samplings. These "holes" in the surface are commonly filled with a smooth patch that conforms with the boundary. We introduce a context-based method: the characteristics of the given surface are analyzed, and the hole is iteratively filled by copying patches from valid regions of the given surface. In particular, the method needs to determine best matching patches, and then, fit imported patches by aligning them with the surrounding surface. The completion process works top down, where details refine intermediate coarser approximations. To align an imported patch with the existing surface, we apply a rigid transformation followed by an iterative closest point procedure with non-rigid transformations. The surface is essentially treated as a point set, and local implicit approximations aid in measuring the similarity between two point set patches. We demonstrate the method at several point-sampled surfaces, where the holes either result from imperfect sampling during range scanning or manual removal.

We introduce an example-based synthesis technique that extrapolates novel styles for a given input image. The technique is based on separating the style and content of image fragments. Given an image with a new style and content, it is first adaptively partitioned into fragments. Stitching together novel fragments produces a coherent image in a new style for a given content. The aggregate of synthesized fragments approximates a globally non-linear model with a set of locally linear models. We show the result of our method for various artistic, sketch, and texture filters and painterly styles applied to different image content classes.

In this paper, we revisit the cells-and-portals visibility methods, originally developed for the special case of architectural interiors. We define an effectiveness measure for a cells-and-portals partitioning, and introduce a two-pass algorithm that computes a cells-and-portals partition. The algorithm uses a simple heuristic that creates short portals as a mean for generating an effective partition. The input to the algorithm is a set of half edges in 2D that can be extracted from a complex polygonal model. The first pass of the algorithm creates an initial partition, which is then refined by the second pass. We show that our method creates a partition that is more effective than the common BSP partition, even when the latter is further refined with the application of our second pass. Our cells-and-portals algorithm is designed to deal with arbitrarily oriented walls. The algorithm also supports outdoor scenes, where the vertical walls of the buildings served as occluders and portals are extended above the buildings. We show that the extended portals allow an output-sensitive rendering of large urban scenes. Finally, since our two-pass method is fully automatic and local, it supports incremental changes of the model by locally recomputing and updating the partition. We call our method "Breaking the Walls" (BW) since it breaks out of indoor scenes to outdoor scenes, and allows walls to be broken interactively, with an instant updating of the partition.

Abstract We present a context‐based scanning algorithm which reorders the input image using a hierarchical representationof the image. Our algorithm optimally orders (permutes) the leaves corresponding to the pixels, by minimizing thesum of distances between neighboring pixels. The reordering results in an improved autocorrelation betweennearby pixels which leads to a smoother image. This allows us, for the first time, to improve image compressionrates using context‐based scans. The results presented in this paper greatly improve upon previous work in bothcompression rate and running time. Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computer Graphics]: Computational Geometryand Object Modeling I.3.6 [Computer Graphics]: Methodology and Techniques

We present a new method for completing missing parts caused by the removal of foreground or background elements from an image. Our goal is to synthesize a complete, visually plausible and coherent image. The visible parts of the image serve as a training set to infer the unknown parts. Our method iteratively approximates the unknown regions and composites adaptive image fragments into the image. Values of an inverse matte are used to compute a confidence map and a level set that direct an incremental traversal within the unknown area from high to low confidence. In each step, guided by a fast smooth approximation, an image fragment is selected from the most similar and frequent examples. As the selected fragments are composited, their likelihood increases along with the mean confidence of the image, until reaching a complete image. We demonstrate our method by completion of photographs and paintings.

Progressive point set surfaces (PPSS) are a multilevel point-based surface representation. They combine the usability of multilevel scalar displacement maps (e.g., compression, filtering, geometric modeling) with the generality of point-based surface representations (i.e., no fixed homology group or continuity class). The multiscale nature of PPSS fosters the idea of point-based modeling. The basic building block for the construction of PPSS is a projection operator, which maps points in the proximity of the shape onto local polynomial surface approximations. The projection operator allows the computing of displacements from smoother to more detailed levels. Based on the properties of the projection operator we derive an algorithm to construct a base point set. Starting from this base point set, a refinement rule using the projection operator constructs a PPSS from any given manifold surface.

We present an anisotropic mesh denoising algorithm that is effective, simple and fast. This is accomplished by filtering vertices of the mesh in the normal direction using local neighborhoods. Motivated by the impressive results of bilateral filtering for image denoising, we adopt it to denoise 3D meshes; addressing the specific issues required in the transition from two-dimensions to manifolds in three dimensions. We show that the proposed method successfully removes noise from meshes while preserving features. Furthermore, the presented algorithm excels in its simplicity both in concept and implementation.

From-region visibility culling is considered harder than from-point visibility culling, since it is inherently four-dimensional. We present a conservative occlusion culling method based on factorizing the 4D visibility problem into horizontal and vertical components. The visibility of the two components is solved asymmetrically: the horizontal component is based on a parameterization of the ray space, and the visibility of the vertical component is solved by incrementally merging umbrae. The technique is designed so that the horizontal and vertical operations can be efficiently realized together by modern graphics hardware. Similar to image-based from-point methods, we use an occlusion map to encode visibility; however, the image-space occlusion map is in the ray space rather than in the primal space. Our results show that the culling time and the size of the computed potentially visible set depend on the size of the viewcell. For moderate viewcells, conservative occlusion culling of large urban scenes takes less than a second, and the size of the potentially visible set is only about two times larger than the size of the exact visible set.

We advocate the use of point sets to represent shapes. We provide a definition of a smooth manifold surface from a set of points close to the original surface. The definition is based on local maps from differential geometry, which are approximated by the method of moving least squares (MLS). The computation of points on the surface is local, which results in an out-of-core technique that can handle any point set. We show that the approximation error is bounded and present tools to increase or decrease the density of the points, thus allowing an adjustment of the spacing among the points to control the error. To display the point set surface, we introduce a novel point rendering technique. The idea is to evaluate the local maps according to the image resolution. This results in high quality shading effects and smooth silhouettes at interactive frame rates.

Visibility algorithms for walkthrough and related applications have grown into a significant area, spurred by the growth in the complexity of models and the need for highly interactive ways of navigating them. In this survey, we review the fundamental issues in visibility and conduct an overview of the visibility culling techniques developed in the last decade. The taxonomy we use distinguishes point-based methods from-region methods. Point-based methods are further subdivided into object and image-precision techniques, while from-region approaches can take advantage of the cell-and-portal structure of architectural environments or handle generic scenes.

Binary-defined 3D objects are common in volume graphics and medical imaging as a result of voxelization algorithms, segmentation methods, and binary operations such as clipping. Traditionally, renderings of binary objects suffer from severe image quality problems, especially when one tries to zoom-in and render the binary data from up close. We present a new rendering technique for discrete binary surfaces. The technique is based on distance-based normal estimation, an accelerated ray casting, and a tricubic interpolator. We demonstrate the quality achieved by our method and report on its interactive rendering speed.

Many computer graphics operations, such as texture mapping, 3D painting, remeshing, mesh compression, and digital geometry processing, require finding a low-distortion parameterization for irregular connectivity triangulations of arbitrary genus 2-manifolds. This paper presents a simple and fast method for computing parameterizations with strictly bounded distortion. The new method operates by flattening the mesh onto a region of the 2D plane. To comply with the distortion bound, the mesh is automatically cut and partitioned on-the-fly. The method guarantees avoiding global and local self-intersections, while attempting to minimize the total length of the introduced seams. To our knowledge, this is the first method to compute the mesh partitioning and the parameterization simultaneously and entirely automatically, while providing guaranteed distortion bounds. Our results on a variety of objects demonstrate that the method is fast enough to work with large complex irregular meshes in interactive applications.

We advocate the use of point sets to represent shapes. We provide a definition of a smooth manifold surface from a set of points close to the original surface. The definition is based on local maps from differential geometry, which are approximated by the method of moving least squares (MLS). We present tools to increase or decrease the density of the points, thus, allowing an adjustment of the spacing among the points to control the fidelity of the representation. To display the point set surface, we introduce a novel point rendering technique. The idea is to evaluate the local maps according to the image resolution. This results in high quality shading effects and smooth silhouettes at interactive frame rates.

We present a new compression algorithm for video sequences of indoor scenes, or more generally, sequences containing mostly planar and near-planar surfaces. Our approach utilizes edge and optical flow information in order to segment selected keyframes into regions of general shape, such that the motion of each region is predicted well by a planar homography. With this kind of motion prediction, the errors between the predicted intermediate frames and the actual ones are very small, and can be compactly encoded. Our results demonstrate significant improvements in the accuracy of the compressed video sequences, compared to standard general purpose video compression.

We present an object-space morphing technique that blends the interiors of given two- or three-dimensional shapes rather than their boundaries. The morph is rigid in the sense that local volumes are least-distorting as they vary from their source to target configurations. Given a boundary vertex correspondence, the source and target shapes are decomposed into isomorphic simplicial complexes. For the simplicial complexes, we find a closed-form expression allocating the paths of both boundary and interior vertices from source to target locations as a function of time. Key points are the identification of the optimal simplex morphing and the appropriate definition of an error functional whose minimization defines the paths of the vertices. Each pair of corresponding simplices defines an affine transformation, which is factored into a rotation and a stretching transformation. These local transformations are naturally interpolated over time and serve as the basis for composing a global coherent least-distorting transformation.

A context‐based scanning technique for images is presented. An image is scanned along a context‐based space filling curve that is computed so as to exploit inherent coherence in the image. The resulting one‐dimensional representation of the image has improved autocorrelation compared with universal scans such as the Peano‐Hilbert space filling curve. An efficient algorithm for computing context‐based space filling curves is presented. We also discuss the potential of improved autocorrelation of context‐based space filling curves for image and video lossless compression.

We present an automatic camera placement method for generating image‐based models from scenes with known geometry. Our method first approximately determines the set of surfaces visible from a given viewing area and then selects a small set of appropriate camera positions to sample the scene from. We define a quality measure for a surface as seen, or covered, from the given viewing area. Along with each camera position, we store the set of surfaces which are best covered by this camera. Next, one reference view is generated from each camera position by rendering the scene. Pixels in each reference view that do not belong to the selected set of polygons are masked out. The image‐based model generated by our method, covers every visible surface only once, associating it with a camera position from which it is covered with quality that exceeds a user‐specified quality threshold. The result is a compact non‐redundant image‐based model with controlled quality. The problem of covering every visible surface with a minimum number of cameras (guards) can be regarded as an extension to the well‐known Art Gallery Problem. However, since the 3D polygonal model is textured, the camera‐polygon visibility relation is not binary; instead, it has a weight — the quality of the polygon's coverage.

We present an automatic camera placement method for generating image-based models from scenes with known geometry. Our method first approximately determines the set of surfaces visible from a given viewing area and then selects a small set of appropriate camera positions to sample the scene from. We define a quality measure for a surface as seen, or covered, from the given viewing area. Along with each camera position, we store the set of surfaces which are best covered by this camera. Next, one reference view is generated from each reference view that do not belong to the selected set of polygons are masked out. The image-based model generated by our method, covers every visible surface only once, associating it with a camera position from which it is covered with quality that exceeds a user-specified quality threshold. The result is a compact non-redundant image-based model with controlled quality. The problem of covering every visible surface with a minimum number of cameras (guards) can be regarded as an extension to the well-known Art Gallery Problem. However, since the 3D polygonal model is textured, the camera-polygon visibility relation is not binary; instead, it has a weight-the quality of the polygon's coverage.

This paper presents a streaming technique for synthetic texture intensive 3D animation sequences.There is a short latency time while downloading the animation, until an initial fraction of the compressed data is read by the client.As the animation is played, the remainder of the data is streamed online seamlessly to the client.The technique exploits frame-to-frame coherence for transmitting geometric and texture streams.Instead of using the original textures of the model, the texture stream consists of view-dependent textures which are generated by rendering offline nearby views.These textures have a strong temporal coherency and can thus be well compressed.As a consequence, the bandwidth of the stream of the view-dependent textures is narrow enough to be transmitted together with the geometry stream over a low bandwidth network.These two streams maintain a small online cache of geometry and view-dependent textures from which the client renders the walkthrough sequence in real-time.The overall data transmitted over the network is an order of magnitude smaller than an MPEG postrendered sequence with an equivalent image quality.

This paper presents an image-based walkthrough technique where reference images are sparsely sampled along a path. The technique relies on a simple user interface for rapid modeling. Simple meshes are drawn to model and represent the underlying scene in each of the reference images. The meshes, consisting of only few polygons for each image are then registered by drawing a single line on each image, called model registration line, to form an aligned 3D model. To synthesize a novel view, two nearby reference images are mapped back onto their models by projective texture-mapping. Since the simple meshes are a crude approximation to the real model in the scene, image feature lines are drawn and used as aligning anchors to further register and blend two views together and form a final novel view. The simplicity of the technique yields rapid, “home-made” image-based walkthroughs. We have produced walkthroughs from a set of photographs to show the effectiveness of the technique.

Ray tracing and Monte-Carlo based global illumination, as well as radiosity and other finite-element based global illumination methods, all require repeated evaluation of quantitative visibility queries, such as: what is the average visibility between a point (a differential area element) and a finite area or volume; or what is the average visibility between two finite areas or volumes. We present a new data structure and an algorithm for rapidly evaluating such queries in complex scenes. The proposed approach utilizes a novel image-based discretization of the space of bounded rays in the scene, constructed in a preprocessing stage. This data structure makes it possible to quickly compute approximate answers to visibility queries. Because visibility queries are computed using a discretization of the space, the execution time is effectively decoupled from the number of geometric primitives in the scene. A potential hazard with the proposed approach is that it might require large amounts of memory, if the data structures are designed in a naive fashion. We discuss ways for representing the discretization in a compact manner while still allowing rapid query evaluation. Preliminary results demonstrate the effectiveness of the proposed approach.

No abstract available.

Computing the visibility of out‐door scenes is often much harder than of in‐door scenes. A typical urban scene, for example, is densely occluded, and it is effective to precompute its visibility space, since from a given point only a small fraction of the scene is visible. The difficulty is that although the majority of objects are hidden, some parts might be visible at a distance in an arbitrary location, and it is not clear how to detect them quickly. In this paper we present a method to partition the viewspace into cells containing a conservative superset of the visible objects. For a given cell the method tests the visibility of all the objects in the scene. For each object it searches for a strong occluder which guarantees that the object is not visible from any point within the cell. We show analytically that in a densely occluded scene, the vast majority of objects are strongly occluded, and the overhead of using conservative visibility (rather than visibility) is small. These results are further supported by our experimental results. We also analyze the cost of the method and discuss its effectiveness.

A view-dependent multiresolution triangulation algorithm is presented for a real-time fly-through. The triangulation of the terrain is generated incrementally on-the-fly during the rendering time. We show that since the view changes smoothly, only a few incremental modifications are required to update the triangulation to a new view. The resulting triangles form a multiresolution Delaunay triangulation which satisfies a predetermined view-dependent error tolerance. The presented method provides a guaranteed-quality mesh since it has control over the global geometric approximation error of the multiresolution view-dependent triangulation. © 1998 John Wiley & Sons, Ltd.

Given two or more objects of general topology, intermediate objects are constructed by a distance field metamorphosis. In the presented method the interpolation of the distance field is guided by a warp function controlled by a set of corresponding anchor points. Some rules for defining a smooth least-distorting warp function are given. To reduce the distortion of the intermediate shapes, the warp function is decomposed into a rigid rotational part and an elastic part. The distance field interpolation method is modified so that the interpolation is done in correlation with the warp function. The method provides the animator with a technique that can be used to create a set of models forming a smooth transition between pairs of a given sequence of keyframe models. The advantage of the new approach is that it is capable of morphing between objects having a different topological genus where no correspondence between the geometric primitives of the models needs to be established. The desired correspondence is defined by an animator in terms of a relatively small number of anchor points

High speed networks which guarantee a minimum quality of service (QoS) enable the development of interactive Web systems. The paper introduces a new paradigm for interaction with complex virtual worlds on the Web, which utilizes both the server and the client simultaneously. The client generates the new views by extrapolating a reference view based on the locally available data, including the model. The server transmits only the data necessary to prevent an accumulation of errors. The model based view extrapolation method avoids the use of textures which are view independent primitives and therefore too expensive to be used in interactive applications over the network.

A view-dependent multiresolution triangulation algorithm is presented for a real-time flythrough. The triangulation of the terrain is generated incrementally on-the-fly during the rendering time. We show that since the view changes smoothly only a few incremental modifications are required to update the triangulation to a new view. The resulting triangles form a multiresolution Delaunay triangulation which satisfies a predetermined view-dependent error tolerance. The presented method provides a guaranteed quality mesh since it has control over the global geometric approximation error of the multiresolution view-dependent triangulation.

The paper introduces a tool for visualizing a multidimensional relevance space. Abstractly, the information to be displayed consists of a large number of objects, a set of features that are likely to be of interest to the user, and some function that measures the relevance level of every object to the various features. The goal is to provide the user with a concise and comprehensible visualization of that information. For the type of applications concentrated on, the exact relevance measures of the objects are not significant. This enables accuracy to be traded for a clearer display. The idea is to "flatten" the multidimensionality of the feature space into a 2D "relevance map", capturing the inter-relations among the features, without causing too many ambiguous interpretations of the results. To better reflect the nature of the data and to resolve the ambiguity the authors refine the given set of features and introduce the notion of composed features. The layout of the map is then obtained by grading it according to a set of rules and using a simulated annealing algorithm which optimizes the layout with respect to these rules. The technique proposed has been implemented and tested, in the context of visualizing the result of a Web search, in the RMAP (Relevance Map) prototype system.

This paper presents a technique to improve the performance of a walkthrough in remote virtual environments, where a scene is rendered jointly by the server and the client, in order to reduce the network requirements as much as possible. The client generates novel views by extrapolating a reference view based on the locally available geometric model, while the server transmits data necessary to prevent an accumulation of errors. Within this concept, we show that by transmitting only a selected subset of pixels, the quality of the extrapolated views can be improved while requiring less bandwidth. We focus on the selection process in which the visibility gaps between the reference view and novel view are detected, packed and transmitted compressed to the client.

The representation of a scene at different levels of detail is necessary to achieve real-time rendering. In aerial views, only the part of the scene that is close to the viewing point needs to be displayed with a high level of detail, while more distant parts can be displayed with a low level of detail. However, when a sequence of images is generated and displayed in real-time, the transition between different levels of detail causes noticeable temporal aliasing. In this paper, we propose a method, based on object blending, that visually softens the transition between two levels of Delaunay triangulation. We present an algorithm that establishes, in an off-line process, a correspondence between two given polygonal objects. The correspondence enables on-line blending between two representations of an object, so that one representation (level of detail) progressively evolves into the other.

Given (n-1)-dimensional parallel cross-sections of an n-dimensional body, one would like to reconstruct the n-dimensional body. The method based on Distance Field Interpolation (DFI) gives a robust solution to this problem in its ability to deal with any topology in any dimension. Still this method may give undesired solutions to the problem if the changes from one cross-section to the next are significant relative to the size of the details in the cross-sections. We consider the problem of solid reconstruction from contours, which can also be considered as a contour blending or contour morphing problem, where the third dimension is time. The method presented is based on interpolation of the distance field, guided by a warp function which is controlled by a set of corresponding anchor points. Some rules for defining a smooth least-distorting warp function are given. To reduce the distortion of the intermediate shapes, the warp function is decomposed into a rigid rotational part and an elastic part. The distance field interpolation method is modified so that the interpolation is guided by the warp function. The advantage of the new approach is that it is capable of blending between contours having different topological genus, and no correspondence between the geometric primitives should be established. The desired general correspondence is defined by the user in terms of a relatively small number of anchor points.

In this paper we present a comprehensive flythrough system which generates photo-realistic images in true real-time. The high performance is due to an innovative rendering algorithm based on a discrete ray casting approach, accelerated by ray coherence and multiresolution traversal. The terrain as well as the 3D objects are represented by a textured mapped voxel-based model. The system is based on a pure software algorithm and is thus portable. It was first implemented on a workstation and then ported to a general-purpose parallel architecture to achieve real-time performance.

Abstract This paper introduces a data distribution scheme and an alignment algorithm for parallel volume rendering. The algorithm performs a single wrap‐around shear transformation which requires only a regular inter‐processor communication pattern. The alignment can be implemented incrementally consisting of short distance shifts, thus significantly reducing the communication overhead. The alignment process is a non‐destructive transformation, consisting of a single non‐scaling shear operation. This is a unique feature which provides the basis for the incremental algorithm.

Abstract The problem of detecting the visible and hidden areas of a topographic surface from a given viewpoint is well known, and has applications in GIS and other fields. The computational geometry literature is rich with solutions based on a polygonal representation of the surface. This work confronts the problem by working directly on the Digital Elevation Map which represents the terrain surface. We present an algorithm that processes discrete lines of sight from the viewpoint to the surface perimeter, and tests the unit‐sized terrain elements along the discrete cross‐sections defined by these lines. The algorithm is very efficient, performing O(n) testing operations, consisting of a few additions and no more than one multiplication each, where n is the number of the terrain elements in the map.

We extend a 2D linear skewed memory organization to 3D and introduce the associated de-skewing scheme designed to provide conflict-free access to projection rays of voxels for use in a volume rendering architecture. This is an application of a 3D linear skewing scheme which supports real-time axonometric projection from 26 primary orientations.>

Abstract We present a method for the generation of photo‐realistic images of views over terrain datasets by mapping a digital aerial photograph on a perspective projection of a digital elevation map. We use high resolution for both digital maps to increase the quality and the realism of the image at the cost of the overhead of processing very large data bases. In the core of this paper we present an accelerated ray casting technique based on a new algorithm of traversing a pyramidal data structure. Unlike other known traversal techniques, the cost of a single step of the algorithm consists of a few additions, shifts and comparisons only.