3D Gaussian Splatting (3DGS) has revolutionized 3D scene representation with superior efficiency and quality. While recent adaptations for computed tomography (CT) show promise, they struggle with severe artifacts under highly sparse-view projections and dynamic motions. To address these challenges, we propose Tomographic Geometry Field (TG-Field), a geometry-aware Gaussian deformation framework tailored for both static and dynamic CT reconstruction. A multi-resolution hash encoder is employed to capture local spatial priors, regularizing primitive parameters under ultra-sparse settings. We further extend the framework to dynamic reconstruction by introducing time-conditioned representations and a spatiotemporal attention block to adaptively aggregate features, thereby resolving spatiotemporal ambiguities and enforcing temporal coherence. In addition, a motion-flow network models fine-grained respiratory motion to track local anatomical deformations. Extensive experiments on synthetic and real-world datasets demonstrate that TG-Field consistently outperforms existing methods, achieving state-of-the-art reconstruction accuracy under highly sparse-view conditions.

In the field of sketch generation, raster-format trained models often produce non-stroke artifacts, while vector-format trained models typically lack a holistic understanding of sketches, leading to compromised recognizability. Moreover, existing methods struggle to extract common features from similar elements (e.g., eyes of animals) appearing at varying positions across sketches. To address these challenges, we propose StrokeFusion, a two-stage framework for vector sketch generation. It contains a dual-modal sketch feature learning network that maps strokes into a high-quality latent space. This network decomposes sketches into normalized strokes and jointly encodes stroke sequences with Unsigned Distance Function (UDF) maps, representing sketches as sets of stroke feature vectors. Building upon this representation, our framework exploits a stroke-level latent diffusion model that simultaneously adjusts stroke position, scale, and trajectory during generation. This enables high-fidelity stroke generation while supporting stroke interpolation editing. Extensive experiments across multiple sketch datasets, demonstrate that our framework outperforms state-of-the-art techniques, validating its effectiveness in preserving structural integrity and semantic features.

Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) for improving reasoning ability of large language models (LLMs).However, this voting strategy often induces confirmation bias and suffers from sparse rewards, limiting the overall performance.In this work, we propose subgroup-specific step-wise confidenceweighted pseudo-label estimation (SCOPE), a framework integrating model confidence and dynamic subgroup partitioning to address these issues.Specifically, SCOPE integrates the proposed step-wise confidence into pseudolabel estimation, prioritizing high-quality reasoning paths over simple frequency count.Furthermore, it dynamically partitions the candidate outputs pool into independent subgroups by balancing reasoning quality against exploration diversity.By deriving local consensus via repeat sampling for each subgroup, SCOPE provides diverse supervision targets to encourage broader exploration.We conduct experiments across various models and benchmarks, experimental results show that SCOPE consistently outperforms recent baselines.Notably, SCOPE achieves relative improvements of 13.1% on challenging AIME 2025 and 8.1% on AMC.The code is released at https://github.com/szu-tera/SCOPE. * ) r(o 3 ,o 2 * ) r(o 5 ,o 3 * ) r(o 7 ,o 4 * ) r(o 2 ,o 1 * ) r(o 4 ,o 2 * ) r(o 6 ,o 3 * ) r(o 8 ,o 4 * ) Now, I'm confident!subgroup1 subgroup2 subgroup3 subgroup4calculate over the entire group dive into confidence?

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.

With the rising ubiquity of digital touch devices and sketch-based interfaces, freehand sketching has become an essential mode of visual communication. Nevertheless, interpreting these often ambiguous and sparse sketches poses challenges for computers. This paper presents Sketchformer++, a hierarchical transformer architecture for the neural representation of vector sketches. It treats a vector sketch as a three-level structure, at sketch level, stroke level, and segment level. Three self-attention modules are adopted in the network architecture, corresponding to the sketch hierarchy. The semantics of sketches are aggregated from local to global levels, resulting in neural representations of sketches. Extensive experiments show that Sketchformer++ helps to achieve superior performance in various downstream tasks, including sketch reconstruction, sketch recog-nition, sketch semantic segmentation, and sketch retrieval, demonstrating its robustness and effectiveness as a means of sketch representation. Code is available at https://github.com/BHR7/SketchformerPlus.

Structured grid layouts are preferable in many 2D visual content creation scenarios since their structures facilitate further layout editing. Multiple geometry-based methods can effectively create structured grid layouts but require user-provided constraints or rules. Existing data-driven approaches have achieved remarkable layout generation performance, but fail to produce appropriate layout structures. We present GTLayout, a novel generative model for structured grid layout generation. We adopt general trees to represent structured grid layouts and exploit a recursive neural network (RvNN) for this generation task. Our model can handle grid layouts with varied structures and regular arrangements. Qualitative and quantitative experiments on public grid layout datasets show that our method outperforms several baselines in the tasks of layout reconstruction and layout generation, especially for datasets containing few samples. We also demonstrate that the structured layout space constructed by our method can blend structures of layouts, as well as providing a visualization and analysis of the layout space. Additionally, we consider two application cases based on GTLayout : multiple layout interpolation and conditional layout generation. Our code is available at https://github.com/Warren-swr/GT-Layout.

Sampling strategies in computer graphics have long been divided between local approaches, which optimize sample distributions independently at each pixel, and global approaches, which use high-dimensional low-discrepancy sequences to ensure uniformity across all dimensions, including adjacent pixels. While global samplers are most-commonly used thanks to generally having better convergence rates, it comes at a cost of very limited user control over the distribution of samples on subspaces, making it difficult to handle common aliasing artifacts. We introduce a novel modular meta-sampler architecture that bridges local and global sampling, allowing integrator designers to employ specialized low-dimensional samplers while still achieving high-dimensional uniformity. Our approach leverages high-dimensional low-discrepancy sequences to orchestrate sample generation by a collection of local samplers operating over power-of-two hierarchical intervals. We demonstrate how existing local sampling techniques, including stratified, blue noise, and dyadic nets sampling, can be reformulated to be used with this framework, enabling hybrid sampling strategies that combine the benefits of both paradigms.

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/.

View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods' stability under inputs with various view transformations. However, existing research seldom focused on view transformation robustness in multi-view 3D object reconstruction. One direct way to improve the models' VTR is to produce data with more view transformations and add them to model training. Recent progress on large vision models, particularly Stable Diffusion models, has provided great potential for generating 3D models or synthesizing novel view images with only a single image input. Directly deploying these models at inference consumes heavy computation resources and their robustness to view transformations is not guaranteed either. To fully utilize the power of Stable Diffusion models without extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness. Instead of synthesizing random views, we propose a reconstruction error-guided view selection method, which considers the reconstruction errors' spatial distribution of the 3D predictions and chooses the views that could cover the reconstruction errors as much as possible. The methods are trained and tested on sets with large view transformations to validate the 3D reconstruction models' robustness to view transformations. Extensive experiments demonstrate that the proposed method can outperform state-of-the-art 3D reconstruction methods and other view transformation robustness comparison methods.

Out-of-distribution (OOD) detection is a crucial task for deploying deep learning models in the wild. One of the major challenges is that well-trained deep models tend to perform over-confidence on unseen test data. Recent research attempts to leverage real or synthetic outliers to mitigate the issue, which may significantly increase computational costs and be biased toward specific outlier characteristics. In this paper, we propose a simple yet effective framework, Prototypical Outlier Proxy (POP), which introduces virtual OOD prototypes to reshape the decision boundaries between ID and OOD data. Specifically, we transform the learnable classifier into a fixed one and augment it with a set of prototypical weight vectors. Then, we introduce a hierarchical similarity boundary loss to impose adaptive penalties depending on the degree of misclassification. Extensive experiments across various benchmarks demonstrate the effectiveness of POP. Notably, POP achieves average FPR95 reductions of 7.70%, 6.30%, and 5.42% over the second-best methods on CIFAR-10, CIFAR-100, and ImageNet-200, respectively. Moreover, compared to the recent method NPOS, which relies on outlier synthesis, POP trains 7.2 times faster and performs inference 19.5 times faster.

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.

We introduce ArcPro, a novel learning framework built on architectural programs to recover structured 3D abstractions from highly sparse and low-quality point clouds. Specifically, we design a domain-specific language (DSL) to hierarchically represent building structures as a program, which can be efficiently converted into a mesh. We bridge feedforward and inverse procedural modeling by using a feedforward process for training data synthesis, allowing the network to make reverse predictions. We train an encoder-decoder on the points-program pairs to establish a mapping from unstructured point clouds to architectural programs, where a 3D convolutional encoder extracts point cloud features and a transformer decoder autoregressively predicts the programs in a tokenized form. Inference by our method is highly efficient and produces plausible and faithful 3D abstractions. Comprehensive experiments demonstrate that ArcPro outperforms both traditional architectural proxy reconstruction and learning-based abstraction methods. We further explore its potential to work with multi-view image and natural language inputs. Project page: https://vcc.tech/research/2025/ArcPro.

Recent advances in generative diffusion models have shown a notable inherent understanding of image style and semantics. In this paper, we leverage the self-attention features from pretrained diffusion networks to transfer the visual characteristics from a reference to generated images. Unlike previous work that uses these features as plug-and-play attributes, we propose a novel attention distillation loss calculated between the ideal and current stylization results, based on which we optimize the synthesized image via backpropagation in latent space. Next, we propose an improved Classifier Guidance that integrates attention distillation loss into the denoising sampling process, further accelerating the synthesis and enabling a broad range of image generation applications. Extensive experiments have demonstrated the extraordinary performance of our approach in transferring the examples’ style, appearance, and texture to new images in synthesis. Code is available at https://github.com/xugao97/AttentionDistillation.

People often need guidance to complete tasks with specific requirements or sophisticated steps, such as preparing a meal or assembling furniture. Traditional guidance often relies on unstructured paper instructions that require people to switch between reading instructions and performing actions, resulting in an unsmooth user experience. Recent Mixed Reality (MR) systems alleviate this problem by giving spatialized navigation but demand an authoring step and, therefore, cannot be easily adapted to general tasks. We propose MRPilot, an MR system empowered by Large Language Models (LLMs) and Computer Vision techniques, offering responsive navigation for general tasks without pre-authoring. MRPilot consists of three modules: a Navigation Builder Module using LLMs to generate structured instructions, an Object Anchor Module exploiting Computer Vision techniques to anchor physical objects with virtual proxies, and an Action Recommendation Module giving responsive navigation according to users’ interactions with physical objects. MRPilot bridges the gap between virtual instructions and physical interactions for general tasks, providing contextual and responsive navigation. We conducted a user study to compare MRPilot with a baseline MR system that also exploited LLMs. The results confirmed the effectiveness of MRPilot.

Abstract Although recent text‐to‐image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style‐Prompting Guidance (SPG), a novel sampling strategy for style‐specific image generation. SPG constructs a style noise vector and leverages its directional deviation from unconditional noise to guide the diffusion process toward the target style distribution. By integrating SPG with Classifier‐Free Guidance (CFG), our method achieves both semantic fidelity and style consistency. SPG is simple, robust, and compatible with controllable frameworks like ControlNet and IPAdapter, making it practical and widely applicable. Extensive experiments demonstrate the effectiveness and generality of our approach compared to state‐of‐the‐art methods. Code is available at https://github.com/Rumbling281441/SPG .

Abstract Textures are a key component of 3D assets. Transferring textures from one shape to another, without user interaction or additional semantic guidance, is a classical yet challenging problem. It can enhance the diversity of existing shape collections, augmenting their application scope. This paper proposes an innovative 3D texture transfer framework that leverages the generative power of pre‐trained diffusion models. While diffusion models have achieved significant success in 2D image generation, their application to 3D domains faces great challenges in preserving coherence across different viewpoints. Addressing this issue, we designed a multi‐scale generation framework to optimize the UV maps coarse‐to‐fine. To ensure multi‐view consistency, we use depth info as geometric guidance; meanwhile, a novel consistency loss is proposed to further constrain the color coherence and reduce artifacts. Experimental results demonstrate that our multi‐scale framework not only produces high‐quality texture transfer results but also excels in handling complex shapes while preserving correct semantic correspondences. Compared to existing techniques, our method achieves improvements in both consistency and texture clarity, as well as time efficiency.

Abstract Recently, 2D Gaussian Splatting (2DGS) has demonstrated superior geometry reconstruction quality than the popular 3DGS by using 2D surfels to approximate thin surfaces. However, it falls short when dealing with glossy surfaces, resulting in visible holes in these areas. We find that the reflection discontinuity causes the issue. To fit the jump from diffuse to specular reflection at different viewing angles, depth bias is introduced in the optimized Gaussian primitives. To address that, we first replace the depth distortion loss in 2DGS with a novel depth convergence loss, which imposes a strong constraint on depth continuity. Then, we rectify the depth criterion in determining the actual surface, which fully accounts for all the intersecting Gaussians along the ray. Qualitative and quantitative evaluations across various datasets reveal that our method significantly improves reconstruction quality, with more complete and accurate surfaces than 2DGS. Code is available at https://github.com/XiaoXinyyx/Unbiased_Surfel .

Cartoonizing portrait images is a stylish and eye-catching application in both computer vision and graphics. We aimed to train a face cartoonization model using very few (e.g., 5–10) style examples. The main difficulty in this challenging task lies in producing stylizations of high quality while preserving the identity of the input, particularly when the style examples contain strong exaggerations. To address this, we propose a novel cross-domain center loss for few-shot generative adversarial network (GAN) adaptation, which forces the distribution of the target domain to be similar to that of the source. We then employ it to solve this few-shot problem along with a two-stage strategy. Stage I generates an intermediate cartoonization for the input, where we first stylize the individual facial components locally and then deform them to mimic the desired exaggeration under the guidance of landmarks. Stage II focuses on global refinement of the intermediate image. First, we adapt a pretrained StyleGAN model using the proposed cross-domain center loss to the target domain defined by a few examples. Subsequently, the intermediate cartoonization from Stage I can be holistically refined through GAN inversion. The generative power of StyleGAN guarantees high image quality, while the local translation and landmark-guided deformation applied to facial components provide high identity fidelity. Experiments show that the proposed method outperforms state-of-the-art few-shot stylization approaches both qualitatively and quantitatively.

Low-discrepancy sequences have seen widespread adoption in computer graphics thanks to the superior rates of convergence that they provide. Because rendering integrals often are comprised of products of lower-dimensional integrals, recent work has focused on developing sequences that are also well-distributed in lower-dimensional projections. To this end, we introduce a novel construction of binary-based (0, 4)-sequences; that is, progressive fully multi-stratified sequences of 4D points, and extend the idea to higher power-of-two dimensions. We further show that not only it is possible to nest lower-dimensional sequences in higher-dimensional ones—for example, embedding a (0, 2)-sequence within our (0, 4)-sequence—but that we can ensemble two (0, 2)-sequences into a (0, 4)-sequence, four (0, 4)-sequences into a (0,16)-sequence, and so on. Such sequences can provide excellent rates of convergence when integrals include lower-dimensional integration problems in 2, 4, 16,... dimensions. Our construction is based on using 2×2 block matrices as symbols to construct larger matrices that potentially generate a sequence with the target (0, s )-sequence in base s property. We describe how to search for suitable alphabets and identify two distinct, cross-related alphabets of block symbols, which we call s and z , hence SZ for the resulting family of sequences. Given the alphabets, we construct candidate generator matrices and search for valid sets of matrices. We then infer a simple recurrence formula to construct full-resolution (64-bit) matrices. Because our generator matrices are binary, they allow highly-efficient implementation using bitwise operations and can be used as a drop-in replacement for Sobol matrices in existing applications. We compare SZ sequences to state-of-the-art low discrepancy sequences, and demonstrate mean relative squared error improvements up to 1.93× in common rendering applications.

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.

Recent advances in image acquisition and scene reconstruction have enabled the generation of high-quality structural urban scene geometry, given sufficient site information. However, current capture techniques often overlook the crucial importance of texture quality, resulting in noticeable visual artifacts in the textured models. In this work, we introduce the urban geometry and texture co-capture problem under limited prior knowledge before a site visit. The only inputs are a 2D building contour map of the target area and a safe flying altitude above the buildings. We propose an innovative aerial path planning framework designed to co-capture images for reconstructing both structured geometry and high-fidelity textures. To evaluate and guide view planning, we introduce a comprehensive texture quality assessment system, including two novel metrics tailored for building facades. Firstly, our method generates high-quality vertical dipping views and horizontal planar views to effectively capture both geometric and textural details. A multi-objective optimization strategy is then proposed to jointly maximize texture fidelity, improve geometric accuracy, and minimize the cost associated with aerial views. Furthermore, we present a sequential path planning algorithm that accounts for texture consistency during image capture. Extensive experiments on large-scale synthetic and real-world urban datasets demonstrate that our approach effectively produces image sets suitable for concurrent geometric and texture reconstruction, enabling the creation of realistic, textured scene proxies at low operational cost.

Structured layouts are preferable in many 2D visual contents (e.g., GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input. Existing data-driven approaches are effective in automatically generating fixed layouts but fail to produce layout structures. We present StructLayoutFormer, a novel Transformer-based approach for conditional structured layout generation. We use a structure serialization scheme to represent structured layouts as sequences. To better control the structures of generated layouts, we disentangle the structural information from the element placements. Our approach is the first data-driven approach that achieves conditional structured layout generation and produces realistic layout structures explicitly. We compare our approach with existing data-driven layout generation approaches by including post-processing for structure extraction. Extensive experiments have shown that our approach exceeds these baselines in conditional structured layout generation. We also demonstrate that our approach is effective in extracting and transferring layout structures.

Point cloud registration is a classical topic in the field of 3D Vision and Computer Graphics. Generally, the implementation of registration is typically sensitive to similarity transformations (translation, scaling, and rotation), noisy points, and incomplete geometric structures. Especially, the non-uniform scales and defective parts of point clouds increase probability of struck local optima in registration task. In this paper, we propose a robust point cloud registration PKSS-Align that can handle various influences, including similarity transformations, non-uniform densities, random noisy points, and defective parts. The proposed method measures shape feature-based similarity between point clouds on the Pre-Kendall shape space (PKSS), which is a shape measurement-based scheme and doesn't require point-to-point or point-to-plane metric. The employed measurement can be regarded as the manifold metric that is robust to various representations in the euclidean coordinate system. Benefited from the measurement, the transformation matrix can be directly generated for point clouds with mentioned influences at the same time. The proposed method does not require data training and complex feature encoding. Based on a simple parallel acceleration, it can achieve significant improvement for efficiency and feasibility in practice. Experiments demonstrate that our method outperforms the relevant state-of-the-art methods.

The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model's generalization ability and enable more practical evaluation and comparison. The model's performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance.

Recent years have witnessed remarkable progress in image generation task, where users can create visually astonishing images with high-quality. However, existing text-to-image diffusion models are proficient in generating concrete concepts (dogs) but encounter challenges with more abstract ones (emotions). Several efforts have been made to modify image emotions with color and style adjustments, facing limitations in effectively conveying emotions with fixed image contents. In this work, we introduce Emotional Image Content Generation (EICG), a new task to generate semantic-clear and emotion-faithful images given emotion categories. Specifically, we propose an emotion space and construct a mapping network to align it with the powerful Contrastive Language-Image Pre-training (CLIP) space, providing a concrete interpretation of abstract emotions. Attribute loss and emotion confidence are further proposed to ensure the semantic diversity and emotion fidelity of the generated images. Our method outperforms the state-of-the-art text-to-image approaches both quantitatively and qualitatively, where we derive three custom metrics, i.e., emotion accuracy, semantic clarity and semantic diversity. In addition to generation, our method can help emotion understanding and inspire emotional art design. Project page: https://vcc.tech/research/2024/EmoGen.

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

This paper addresses the complex issue of one-shot face stylization, focusing on the simultaneous consideration of appearance and structure, where previous methods have fallen short. We explore deformation-aware face stylization that diverges from traditional single-image style reference, opting for a real-style image pair instead. The cornerstone of our method is the utilization of a self-supervised vision transformer, specifically DINO-ViT, to establish a robust and consistent facial structure representation across both real and style domains. Our stylization process begins by adapting the StyleGAN generator to be deformation-aware through the integration of spatial transformers (STN). We then introduce two innovative constraints for generator fine-tuning under the guidance of DINO semantics: i) a directional deformation loss that regulates directional vectors in DINO space, and ii) a relative structural consistency constraint based on DINO token self-similarities, ensuring diverse generation. Additionally, style-mixing is employed to align the color generation with the reference, minimizing inconsistent correspondences. This framework delivers enhanced deformability for general one-shot face stylization, achieving notable efficiency with a fine-tuning duration of approximately 10 minutes. Extensive qualitative and quantitative comparisons demonstrate our superiority over state-of-the-art one-shot face stylization methods. Code is available at https://github.com/zichongc/DoesFS.

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories of images, poses a challenge for the development of 3D pre-trained models. This paper therefore attempts to directly leverage pre-trained models with 2D prior knowledge to accomplish the tasks for 3D point cloud analysis. Accordingly, we propose the Adaptive PointFormer (APF), which fine-tunes pre-trained 2D models with only a modest number of parameters to directly process point clouds, obviating the need for mapping to images. Specifically, we convert raw point clouds into point embeddings for aligning dimensions with image tokens. Given the inherent disorder in point clouds, in contrast to the structured nature of images, we then sequence the point embeddings to optimize the utilization of 2D attention priors. To calibrate attention across 3D and 2D domains and reduce computational overhead, a trainable PointFormer with a limited number of parameters is subsequently concatenated to a frozen pre-trained image model. Extensive experiments on various benchmarks demonstrate the effectiveness of the proposed APF. The source code and more details are available at https://vcc.tech/research/2024/PointFormer.

Synchronized dual-arm rearrangement is widely studied as a common scenario in industrial applications. It often faces scalability challenges due to the computational complexity of robotic arm rearrangement and the high-dimensional nature of dual-arm planning. To address these challenges, we formulated the problem as cooperative mTSP, a variant of mTSP where agents share cooperative costs, and utilized reinforcement learning for its solution. Our approach involved representing rearrangement tasks using a task state graph that captured spatial relationships and a cooperative cost matrix that provided details about action costs. Taking these representations as observations, we designed an attention-based network to effectively combine them and provide rational task scheduling. Furthermore, a cost predictor is also introduced to directly evaluate actions during both training and planning, significantly expediting the planning process. Our experimental results demonstrate that our approach outperforms existing methods in terms of both performance and planning efficiency.

Long-tailed visual recognition has received increasing attention recently. Despite fine-tuning techniques represented by visual prompt tuning (VPT) achieving substantial performance improvement by leveraging pre-trained knowledge, models still exhibit unsatisfactory generalization performance on tail classes. To address this issue, we propose a novel optimization strategy called Gaussian neighborhood minimization prompt tuning (GNM-PT), for VPT to address the long-tail learning problem. We introduce a novel Gaussian neighborhood loss, which provides a tight upper bound on the loss function of data distribution, facilitating a flattened loss landscape correlated to improved model generalization. Specifically, GNM-PT seeks the gradient descent direction within a random parameter neighborhood, independent of input samples, during each gradient update. Ultimately, GNM-PT enhances generalization across all classes while simultaneously reducing computational overhead. The proposed GNM-PT achieves state-of-the-art classification accuracies of 90.3%, 76.5%, and 50.1% on benchmark datasets CIFAR100-LT (IR 100), iNaturalist 2018, and Places-LT, respectively. The source code is available at https://github.com/Keke921/GNM-PT.

Since deep learning models are usually deployed in non-stationary environments, it is imperative to improve their robustness to out-of-distribution (OOD) data. A common approach to mitigate distribution shift is to regularize internal representations or predictors learned from in-distribution (ID) data to be domain invariant. Past studies have primarily learned pairwise invariances, ignoring the intrinsic structure and high-order dependencies of the data. Unlike machines, human recognizes objects by first dividing them into major components and then identifying the topological relation of these components. Motivated by this, we propose Reconstruct and Match (REMA), a general learning framework for object recognition tasks to endow deep models with the capability of capturing the topological homogeneity of objects without human prior knowledge or fine-grained annotations. To identify major components from objects, REMA introduces a selective slot-based reconstruction module to dynamically map dense pixels into a sparse and discrete set of slot vectors in an unsupervised manner. Then, to model high-order dependencies among these components, we propose a hypergraph-based relational reasoning module that models the intricate relations of nodes (slots) with structural constraints. Experiments on standard benchmarks show that REMA outperforms state-of-the-art methods in OOD generalization and test-time adaptation settings.

We introduce camera ray matching (CRAYM) into the joint optimization of camera poses and neural fields from multi-view images. The optimized field, referred to as a feature volume, can be “probed” by the camera rays for novel view synthesis (NVS) and 3D geometry reconstruction. One key reason for matching camera rays, instead of pixels as in prior works, is that the camera rays can be parameterized by the feature volume to carry both geometric and photometric information. Multi-view consistencies involving the camera rays and scene rendering can be naturally integrated into the joint optimization and network training, to impose physically meaningful constraints to improve the final quality of both the geometric reconstruction and photorealistic rendering. We formulate our per-ray optimization and matched ray coherence by focusing on camera rays passing through keypoints in the input images to elevate both the efficiency and accuracy of scene correspondences. Accumulated ray features along the feature volume provide a means to discount the coherence constraint amid erroneous ray matching. We demonstrate the effectiveness of CRAYM for both NVS and geometry reconstruction, over dense- or sparse-view settings, with qualitative and quantitative comparisons to state-of-the-art alternatives.

Abstract We present GLTScene, a novel data‐driven method for high‐quality furniture layout synthesis with general room boundaries as conditions. This task is challenging since the existing indoor scene datasets do not cover the variety of general room boundaries. We incorporate the interior design principles with learning techniques and adopt a global‐to‐local strategy for this task. Globally, we learn the placement of furniture objects from the datasets without considering their alignment. Locally, we learn the alignment of furniture objects relative to their nearest walls, according to the alignment principle in interior design. The global placement and local alignment of furniture objects are achieved by two transformers respectively. We compare our method with several baselines in the task of furniture layout synthesis with general room boundaries as conditions. Our method outperforms these baselines both quantitatively and qualitatively. We also demonstrate that our method can achieve other conditional layout synthesis tasks, including object‐level conditional generation and attribute‐level conditional generation. The code is publicly available at https://github.com/WWalter-Lee/GLTScene .

We introduce deformable interaction analogy (DINA) as a means to generate close interactions between two 3D objects. Given a single demo interaction between an anchor object (e.g. a hand) and a source object (e.g. a mug grasped by the hand), our goal is to generate many analogous 3D interactions between the same anchor object and various new target objects (e.g. a toy airplane), where the anchor object is allowed to be rigid or deformable. To this end, we optimize the pose or shape of the anchor object to adapt it to a new target object to mimic the demo. To facilitate the optimization, we advocate using interaction interface (ITF), defined by a set of points sampled on the anchor object, as a descriptive and robust interaction representation that is amenable to non-rigid deformation. We model similarity between interactions using ITF, while for interaction analogy, we transform the ITF, either rigidly or non-rigidly, to guide the feature matching to the reposing and deformation of the anchor object. Qualitative and quantitative experiments show that our ITF-guided deformable interaction analogy works surprisingly well even with simple distance features compared to variants of state-of-the-art methods that utilize more sophisticated interaction representations and feature learning from large datasets.

Since the preparation of labeled data for training semantic segmentation networks of point clouds is a time-consuming process, weakly supervised approaches have been introduced to learn from only a small fraction of data. These methods are typically based on learning with contrastive losses while automatically deriving per-point pseudo-labels from a sparse set of user-annotated labels. In this paper, our key observation is that the selection of which samples to annotate is as important as how these samples are used for training. Thus, we introduce a method for weakly supervised segmentation of 3D scenes that combines self-training with active learning. Active learning selects points for annotation that are likely to result in improvements to the trained model, while self-training makes efficient use of the user-provided labels for learning the model. We demonstrate that our approach leads to an effective method that provides improvements in scene segmentation over previous work and baselines, while requiring only a few user annotations.

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.

Abstract Exemplar-based image translation involves converting semantic masks into photorealistic images that adopt the style of a given exemplar. However, most existing GAN-based translation methods fail to produce photorealistic results. In this study, we propose a new diffusion model-based approach for generating high-quality images that are semantically aligned with the input mask and resemble an exemplar in style. The proposed method trains a conditional denoising diffusion probabilistic model (DDPM) with a SPADE module to integrate the semantic map. We then used a novel contextual loss and auxiliary color loss to guide the optimization process, resulting in images that were visually pleasing and semantically accurate. Experiments demonstrate that our method outperforms state-of-the-art approaches in terms of both visual quality and quantitative metrics.

Digitalization of large-scale urban scenes (in particular buildings) has been a long-standing open problem, which attributes to the challenges in data acquisition, such as incomplete scene coverage, lack of semantics, low efficiency, and low reliability in path planning. In this paper, we address these challenges in urban building reconstruction from aerial images, and we propose an effective workflow and a few novel algorithms for efficient 3D building instance proxy reconstruction for large urban scenes. Specifically, we propose a novel learning-based approach to instance segmentation of urban buildings from aerial images followed by a voting-based algorithm to fuse the multi-view instance information to a sparse point cloud (reconstructed using a standard Structure from Motion pipeline). Our method enables effective instance segmentation of the building instances from the point cloud. We also introduce a layer-based surface reconstruction method dedicated to the 3D reconstruction of building proxies from extremely sparse point clouds. Extensive experiments on both synthetic and real-world aerial images of large urban scenes have demonstrated the effectiveness of our approach. The generated scene proxy models can already provide a promising 3D surface representation of the buildings in large urban scenes, and when applied to aerial path planning, the instance-enhanced building proxy models can significantly improve data completeness and accuracy, yielding highly detailed 3D building models.

In this paper, we introduce a new method for the task of interaction transfer. Given an example interaction between a source object and an agent, our method can automatically infer both surface and spatial relationships for the agent and target objects within the same category, yielding more accurate and valid transfers. Specifically, our method characterizes the example interaction using a combined spatial and surface representation. We correspond the agent points and object points related to the representation to the target object space using a learned spatial and surface correspondence field, which represents objects as deformed and rotated signed distance fields. With the corresponded points, an optimization is performed under the constraints of our spatial and surface interaction representation and additional regularization. Experiments conducted on human-chair and hand-mug interaction transfer tasks show that our approach can handle larger geometry and topology variations between source and target shapes, significantly outperforming state-of-the-art methods.

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.

We present a novel topology-preserving 3D medial axis computation framework based on volumetric restricted power diagram (RPD), while preserving the medial features and geometric convergence simultaneously, for both 3D CAD and organic shapes. The volumetric RPD discretizes the input 3D volume into sub-regions given a set of medial spheres. With this intermediate structure, we convert the homotopy equivalency between the generated medial mesh and the input 3D shape into a localized contractibility checking for each restricted element (power cell, power face, power edge), by checking their connected components and Euler characteristics. We further propose a fractional Euler characteristic algorithm for efficient GPU-based computation of Euler characteristic for each restricted element on the fly while computing the volumetric RPD. Compared with existing voxel-based or point-cloud-based methods, our approach is the first to adaptively and directly revise the medial mesh without globally modifying the dependent structure, such as voxel size or sampling density, while preserving its topology and medial features. In comparison with the feature preservation method MATFP [Wang et al. 2022], our method provides geometrically comparable results with fewer spheres and more robustly captures the topology of the input 3D shape.

Managing the level-of-detail (LOD) in architectural models is crucial yet challenging, particularly for effective representation and visualization of buildings. Traditional approaches often fail to deliver controllable detail alongside semantic consistency, especially when dealing with noisy and inconsistent inputs. We address these limitations with Co-LOD , a new approach specifically designed for effective LOD management in architectural modeling. Co-LOD employs shape co-analysis to standardize geometric structures across multiple buildings, facilitating the progressive and consistent generation of LODs. This method allows for precise detailing in both individual models and model collections, ensuring semantic integrity. Extensive experiments demonstrate that Co-LOD effectively applies accurate LOD across a variety of architectural inputs, consistently delivering superior detail and quality in LOD representations.

High-quality image generation is an important topic in digital visualization. As a sub-topic of the research, color transfer is to produce a high-quality image with ideal color scheme learned from the reference one. In this article, we investigate the mainstream methods of color transfer to provide a survey that introduces the related theories and frameworks. Such methods can be divided into three categories: statistical color transfer, semantic-based color transfer, and color transfer for special target. For these mainstream technical routes, we discuss the related research background, technical details, and representative methods. We also exhibit some new trends of the topic according to recent progress. Based on the comparisons, we discuss the unsolved issues of color transfer and potential solutions in future work.

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.

Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological structure and geometric details of 3D objects, this remains a challenging task and the lack of large scale labeled data also constrain the performance of deep learning based approaches. In this paper, we tackle the task of object kinematic motion prediction problem in a semi-weakly supervised manner. Our key observations are two-fold. First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale. Second, semantic part segmentation and mobile part segmentation is not always consistent but it is possible to detect the mobile parts from the underlying 3D structure. Towards this end, we propose a graph neural network to learn the map between hierarchical part-level segmentation and mobile parts parameters, which are further refined based on geometric alignment. This network can be first trained on PartNet-Mobility dataset with fully labeled mobility information and then applied on PartNet dataset with fine-grained and hierarchical part-level segmentation. The network predictions yield a large scale of 3D objects with pseudo labeled mobility information and can further be used for weakly-supervised learning with pre-existing segmentation. Our experiments show there are significant performance boosts with the augmented data for previous method designed for kinematic motion prediction on 3D partial scans.

We introduce anchored radial observations (ARO), a novel shape encoding for learning implicit field representation of 3D shapes that is category-agnostic and generalizable amid significant shape variations. The main idea behind our work is to reason about shapes through partial observations from a set of viewpoints, called anchors. We develop a general and unified shape representation by employing a fixed set of anchors, via Fibonacci sampling, and designing a coordinate-based deep neural network to predict the occupancy value of a query point in space. Differently from prior neural implicit models that use global shape feature, our shape encoder operates on contextual, query-specific features. To predict point occupancy, locally observed shape information from the perspective of the anchors surrounding the input query point are encoded and aggregated through an attention module, before implicit decoding is performed. We demonstrate the quality and generality of our network, coined ARO-Net, on surface reconstruction from sparse point clouds, with tests on novel and unseen object categories, “one-shape” training, and comparisons to state-of-the-art neural and classical methods for reconstruction and tessellation.

Markov random fields (MRFs) are the cornerstone of classical approaches to example-based texture synthesis. Yet, it is not fully valued in the deep learning era. This pa-per aims to re-promote the combination of MRFs and neural networks, i.e., the CNNMRF model, for texture synthesis, with two key observations made. We first propose to compute the Guided Correspondence Distance in the nearest neighbor search, based on which a Guided Correspondence loss is defined to measure the similarity of the output texture to the example. Experiments show that our approach sur-passes existing neural approaches in uncontrolled and con-trolled texture synthesis. More importantly, the Guided Cor-respondence loss can function as a general textural loss in, e.g., training generative networks for real-time controlled synthesis and inversion-based single-image editing. In con-trast, existing textural losses, such as the Sliced Wasserstein loss, cannot work on these challenging tasks.

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.

We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object. Specifically, the NIF is a neural field that encodes the relationship between each spatial point and a given object, where the relative position is defined by a spherical distance function rather than occupancies or signed distances, which are commonly adopted by conventional neural fields but less informative. For a given demo interaction, the corresponding NIT is defined by a set of spatial points sampled in the demo NIF with associated neural features. To better capture the interaction, the points are sampled on the Interaction Bisector Surface (IBS), which consists of points that are equidistant to the two interacting objects and has been used extensively for interaction representation. With both point selection and pointwise features defined for better interaction encoding, NIT effectively guides the feature matching in the NIFs of the new object instances such that the relative poses are optimized to realize the manipulation while imitating the demo interactions. Experiments show that our NIFT solution outperforms state-of-the-art imitation learning methods for object manipulation and generalizes better to objects from new categories.

Image-based rendering (IBR) technique enables presenting real scenes interactively to viewers and hence is a key component for implementing VR telepresence. The quality of IBR results depends on the set of pre-captured views, the rendering algorithm used, and the camera parameters of the novel view to be synthesized. Numerous methods were proposed for optimizing the set of captured images and enhancing the rendering algorithms. However, from which regions IBR methods can synthesize satisfactory results is not yet well studied. In this work, we introduce the concept of renderability, which predicts the quality of IBR results at any given viewpoint and view direction. Consequently, the renderability values evaluated for the 5D camera parameter space form a field, which effectively guides viewpoint/trajectory selection for IBR, especially for challenging large-scale 3D scenes. To demonstrate this capability, we designed 2 VR applications: a path planner that allows users to navigate through sparsely captured scenes with controllable rendering quality and a view selector that provides an overview for a scene from diverse and high quality perspectives. We believe the renderability concept, the proposed evaluation method, and the suggested applications will motivate and facilitate the use of IBR in various interactive settings.

In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structures as well as surface details, given partial input, a fundamental component is a good feature representation that can capture both global structure and local geometric details. We accordingly first propose FSNet, a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local regions. We then integrate FSNet into a coarse-to-fine pipeline for point cloud completion. Specifically, a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud. Next, a point cloud upsampling network is used to generate a dense point cloud from the partial input and the coarse intermediate output. To efficiently exploit local structures and enhance point distribution uniformity, we propose IFNet, a point upsampling module with a self-correction mechanism that can progressively refine details of the generated dense point cloud. We have conducted qualitative and quantitative experiments on ShapeNet, MVP, and KITTI datasets, which demonstrate that our method outperforms state-of-the-art point cloud completion approaches.

State-of-the-art semantic segmentation methods capture the relationship between pixels to facilitate contextual information exchange. Advanced methods utilize fixed pathways for context exchange, lacking the flexibility to harness the most relevant context for each pixel. In this paper, we present Configurable Context Pathways (CCPs), a novel model for establishing pathways for augmenting contextual information. In contrast to previous pathway models, CCPs are learned, leveraging configurable regions to form information flows between pairs of pixels. We propose TAGNet to adaptively configure the regions, which span over the entire image space, driven by the relationships between the remote pixels. Subsequently, the information flows along the pathways are updated gradually by the information provided by sequences of configurable regions, forming more powerful contextual information. We extensively evaluate the traveling, adaption, and gathering (TAG) stages of our network on the public benchmarks, demonstrating that all of the stages successfully improve the segmentation accuracy and help to surpass the state-of-the-art results. The code package is available at: https://github.com/dilincv/TAGNet.

We address the problem of scene-aware activity program generation, which requires decomposing a given activity task into instructions that can be sequentially performed within a target scene to complete the activity. While existing methods have shown the ability to generate rational or executable programs, generating programs with both high rationality and executability still remains a challenge. Hence, we propose a novel method where the key idea is to explicitly combine the language rationality of a powerful language model with dynamic perception of the target scene where instructions are executed, to generate programs with high rationality and executability. Our method iteratively generates instructions for the activity program. Specifically, a two-branch feature encoder operates on a language-based and graph-based representation of the current generation progress to extract language features and scene graph features, respectively. These features are then used by a predictor to generate the next instruction in the program. Subsequently, another module performs the predicted action and updates the scene for perception in the next iteration. Extensive evaluations are conducted on the VirtualHome-Env dataset, showing the advantages of our method over previous work. Key algorithmic designs are validated through ablation studies, and results on other types of inputs are also presented to show the generalizability of our method.

Coarse architectural models are often generated at scales ranging from individual buildings to scenes for downstream applications such as Digital Twin City, Metaverse, LODs, etc. Such piece-wise planar models can be abstracted as twins from 3D dense reconstructions. However, these models typically lack realistic texture relative to the real building or scene, making them unsuitable for vivid display or direct reference. In this paper, we present TwinTex , the first automatic texture mapping framework to generate a photorealistic texture for a piece-wise planar proxy. Our method addresses most challenges occurring in such twin texture generation. Specifically, for each primitive plane, we first select a small set of photos with greedy heuristics considering photometric quality, perspective quality and facade texture completeness. Then, different levels of line features (LoLs) are extracted from the set of selected photos to generate guidance for later steps. With LoLs, we employ optimization algorithms to align texture with geometry from local to global. Finally, we fine-tune a diffusion model with a multi-mask initialization component and a new dataset to inpaint the missing region. Experimental results on many buildings, indoor scenes and man-made objects of varying complexity demonstrate the generalization ability of our algorithm. Our approach surpasses state-of-the-art texture mapping methods in terms of high-fidelity quality and reaches a human-expert production level with much less effort.

We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via robotic motion planning, to arrive at a compact packing in a target container. The technical core of our method is a neural network for TAP, trained via reinforcement learning (RL), to solve the NP-hard combinatorial optimization problem. Our network simultaneously selects an object to pack and determines the final packing location, based on a judicious encoding of the continuously evolving states of partially observed source objects and available spaces in the target container, using separate encoders both enabled with attention mechanisms. The encoded feature vectors are employed to compute the matching scores and feasibility masks of different pairings of box selection and available space configuration for packing strategy optimization. Extensive experiments, including ablation studies and physical packing execution by a real robot (Universal Robot UR5e), are conducted to evaluate our method in terms of its design choices, scalability, generalizability, and comparisons to baselines, including the most recent RL-based TAP solution. We also contribute the first benchmark for TAP which covers a variety of input settings and difficulty levels.

We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction , and 3D scanning to recover both the exterior and interior , i.e., unexposed, geometries of a target 3D object. Unlike other works in active vision which focus on optimizing camera viewpoints to better investigate the environment, the primary feature of our reconstruction is an analysis of the interactability of various parts of the target object and the ensuing part manipulation by a robot to enable scanning of occluded regions. As a result, an understanding of part articulations of the target object is obtained on top of complete geometry acquisition. Our method operates fully automatically by a Fetch robot with built-in RGBD sensors. It iterates between interaction analysis and interaction-driven reconstruction, scanning and reconstructing detected moveable parts one at a time, where both the articulated part detection and mesh reconstruction are carried out by neural networks. In the final step, all the remaining, non-articulated parts, including all the interior structures that had been exposed by prior part manipulations and subsequently scanned, are reconstructed to complete the acquisition. We demonstrate the performance of our method via qualitative and quantitative evaluation, ablation studies, comparisons to alternatives, as well as experiments in a real environment.

The interpretation of colors in visualizations is facilitated when the assignments between colors and concepts in the visualizations match human's expectations, implying that the colors can be interpreted in a semantic manner. However, manually creating a dataset of suitable associations between colors and concepts for use in visualizations is costly, as such associations would have to be collected from humans for a large variety of concepts. To address the challenge of collecting this data, we introduce a method to extract color-concept associations automatically from a set of concept images. While the state-of-the-art method extracts associations from data with supervised learning, we developed a self-supervised method based on colorization that does not require the preparation of ground truth color-concept associations. Our key insight is that a set of images of a concept should be sufficient for learning color-concept associations, since humans also learn to associate colors to concepts mainly from past visual input. Thus, we propose to use an automatic colorization method to extract statistical models of the color-concept associations that appear in concept images. Specifically, we take a colorization model pre-trained on ImageNet and fine-tune it on the set of images associated with a given concept, to predict pixel-wise probability distributions in Lab color space for the images. Then, we convert the predicted probability distributions into color ratings for a given color library and aggregate them for all the images of a concept to obtain the final color-concept associations. We evaluate our method using four different evaluation metrics and via a user study. Experiments show that, although the state-of-the-art method based on supervised learning with user-provided ratings is more effective at capturing relative associations, our self-supervised method obtains overall better results according to metrics like Earth Mover's Distance (EMD) and Entropy Difference (ED), which are closer to human perception of color distributions.

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.

Relation contexts have been proved to be useful for many challenging vision tasks. In the field of 3D object detection, previous methods have been taking the advantage of context encoding, graph embedding, or explicit relation reasoning to extract relation contexts. However, there exist inevitably redundant relation contexts due to noisy or low-quality proposals. In fact, invalid relation contexts usually indicate underlying scene misunderstanding and ambiguity, which may, on the contrary, reduce the performance in complex scenes. Inspired by recent attention mechanism like Transformer, we propose a novel 3D attention-based relation module (ARM3D). It encompasses object-aware relation reasoning to extract pair-wise relation contexts among qualified proposals and an attention module to distribute attention weights towards different relation contexts. In this way, ARM3D can take full advantage of the useful relation contexts and filter those less relevant or even confusing contexts, which mitigates the ambiguity in detection. We have evaluated the effectiveness of ARM3D by plugging it into several state-of-the-art 3D object detectors and showing more accurate and robust detection results. Extensive experiments show the capability and generalization of ARM3D on 3D object detection. Our source code is available at https://github.com/lanlan96/ARM3D .

Appropriate color mapping for categorical data visualization can significantly facilitate the discovery of underlying data patterns and effectively bring out visual aesthetics. Some systems suggest predefined palettes for this task. However, a predefined color mapping is not always optimal, failing to consider users' needs for customization. Given an input categorical data visualization and a reference image, we present an effective method to automatically generate a coloring that resembles the reference while allowing classes to be easily distinguished. We extract a color palette with high perceptual distance between the colors by sampling dominant and discriminable colors from the image's color space. These colors are assigned to given classes by solving an integer quadratic program to optimize point distinctness of the given chart while preserving the color spatial relations in the source image. We show results on various coloring tasks, with a diverse set of new coloring appearances for the input data. We also compare our approach to state-of-the-art palettes in a controlled user study, which shows that our method achieves comparable performance in class discrimination, while being more similar to the source image. User feedback after using our system verifies its efficiency in automatically generating desirable colorings that meet the user's expectations when choosing a reference.

Autonomous 3D acquisition of outdoor environments poses special challenges. Different from indoor scenes, where the room space is delineated by clear boundaries and separations (e.g., walls and furniture), an outdoor environment is spacious and unbounded (thinking of a campus). Therefore, unlike for indoor scenes where the scanning effort is mainly devoted to the discovery of boundary surfaces, scanning an open and unbounded area requires actively delimiting the extent of scanning region and dynamically planning a traverse path within that region. Thus, for outdoor scenes, we formulate the planning of an energy-efficient autonomous scanning through a discrete-continuous optimization of robot scanning paths. The discrete optimization computes a topological map, through solving an online traveling sales problem (Online TSP), which determines the scanning goals and paths on-the-fly. The dynamic goals are determined as a collection of visit sites with high reward of visibility-to-unknown. A visit graph is constructed via connecting the visit sites with edges weighted by traversing cost. This topological map evolves as the robot scans via deleting outdated sites that are either visited or become rewardless and inserting newly discovered ones. The continuous part optimizes the traverse paths geometrically between two neighboring visit sites via maximizing the information gain of scanning along the paths. The discrete and continuous processes alternate until the traverse cost of the current graph exceeds the remaining energy capacity of the robot. Our approach is evaluated with both synthetic and field tests, demonstrating its effectiveness and advantages over alternatives.

We introduce a method for assigning photorealistic relightable materials to 3D shapes in an automatic manner. Our method takes as input a photo exemplar of a real object and a 3D object with segmentation, and uses the exemplar to guide the assignment of materials to the parts of the shape, so that the appearance of the resulting shape is as similar as possible to the exemplar. To accomplish this goal, our method combines an image translation neural network with a material assignment neural network. The image translation network translates the color from the exemplar to a projection of the 3D shape and the part segmentation from the projection to the exemplar. Then, the material prediction network assigns materials from a collection of realistic materials to the projected parts, based on the translated images and perceptual similarity of the materials. One key idea of our method is to use the translation network to establish a correspondence between the exemplar and shape projection, which allows us to transfer materials between objects with diverse structures. Another key idea of our method is to use the two pairs of (color, segmentation) images provided by the image translation to guide the material assignment, which enables us to ensure the consistency in the assignment. We demonstrate that our method allows us to assign materials to shapes so that their appearances better resemble the input exemplars, improving the quality of the results over the state-of-the-art method, and allowing us to automatically create thousands of shapes with high-quality photorealistic materials. Code and data for this paper are available at https://github.com/XiangyuSu611/TMT.

We introduce the first learning-based reconstructability predictor to improve view and path planning for large-scale 3D urban scene acquisition using unmanned drones. In contrast to previous heuristic approaches, our method learns a model that explicitly predicts how well a 3D urban scene will be reconstructed from a set of viewpoints. To make such a model trainable and simultaneously applicable to drone path planning, we simulate the proxy-based 3D scene reconstruction during training to set up the prediction. Specifically, the neural network we design is trained to predict the scene reconstructability as a function of the proxy geometry , a set of viewpoints, and optionally a series of scene images acquired in flight. To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning. We demonstrate that our data-driven reconstructability predictions are more closely correlated to the true reconstruction quality than prior heuristic measures. Further, our learned predictor can be easily integrated into existing path planners to yield improvements. Finally, we devise a new iterative view planning framework, based on the learned reconstructability, and show superior performance of the new planner when reconstructing both synthetic and real scenes.

We approach the problem of high-DOF reaching-and-grasping via learning joint planning of grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the gripper and the target object. To represent gripper-object interaction, we adopt Interaction Bisector Surface (IBS) which is the Voronoi diagram between two close by 3D geometric objects and has been successfully applied in characterizing spatial relations between 3D objects. We found that IBS is surprisingly effective as a state representation since it well informs the finegrained control of each finger with spatial relation against the target object. This novel grasp representation, together with several technical contributions including a fast IBS approximation, a novel vector-based reward and an effective training strategy, facilitate learning a strong control model of high-DOF grasping with good sample efficiency, dynamic adaptability, and cross-category generality. Experiments show that it generates high-quality dexterous grasp for complex shapes with smooth grasping motions. Code and data for this paper are at https://github.com/qijinshe/IBS-Grasping.

We present a novel method for blending hierarchical layouts with semantic labels. The core of our method is a hierarchical structure correspondence algorithm, which recursively finds optimal substructure correspondences, achieving a globally optimal correspondence between a pair of hierarchical layouts. This correspondence is consistent with the structures of both layouts, allowing us to define the union of the layouts' structures. The resulting compound structure helps extract intermediate layout structures, from which blended layouts can be generated via an optimization approach. The correspondence also defines a similarity measure between layouts in a hierarchically structured view. Our method provides a new way for novel layout creation. The introduced structural similarity measure regularizes the layouts in a hyperspace. We demonstrate two applications in this paper, i.e., exploratory design of novel layouts and sketch-based layout retrieval, and test them on a magazine layout dataset. The effectiveness and feasibility of these two applications are confirmed by the user feedback and the extensive results. The code is available at https://github.com/lyf7115/LayoutBlending.

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.

One of the fundamental tasks in visualization is to compare two or more visual elements. However, it is often difficult to visually differentiate graphical elements encoding a small difference in value, such as the heights of similar bars in bar chart or angles of similar sections in pie chart. Perceptual laws can be used in order to model when and how we perceive this difference. In this work, we model the perception of Just Noticeable Differences (JNDs), the minimum difference in visual attributes that allow faithfully comparing similar elements, in charts. Specifically, we explore the relation between JNDs and two major visual variables: the intensity of visual elements and the distance between them, and study it in three charts: bar chart, pie chart and bubble chart. Through an empirical study, we identify main effects on JND for distance in bar charts, intensity in pie charts, and both distance and intensity in bubble charts. By fitting a linear mixed effects model, we model JND and find that JND grows as the exponential function of variables. We highlight several usage scenarios that make use of the JND modeling in which elements below the fitted JND are detected and enhanced with secondary visual cues for better discrimination.

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.

Abstract In this paper, we study the problem of 3D shape upright orientation estimation from the perspective of reinforcement learning, i.e. we teach a machine (agent) to orientate 3D shapes step by step to upright given its current observation. Unlike previous methods, we take this problem as a sequential decision‐making process instead of a strong supervised learning problem. To achieve this, we propose UprightRL, a deep network architecture designed for upright orientation estimation. UprightRL mainly consists of two submodules: an Actor module and a Critic module which can be learned with a reinforcement learning manner. Specifically, the Actor module selects an action from the action space to perform a point cloud transformation and obtain the new point cloud for the next environment state, while the Critic module evaluates the strategy and guides the Actor to choose the next stage action. Moreover, we design a reward function that encourages the agent to select action which is conducive to orient model towards upright orientation with a positive reward and negative otherwise. We conducted extensive experiments to demonstrate the effectiveness of the proposed model, and experimental results show that our network outperforms the state‐of‐the‐art. We also apply our method to the robot grasping‐and‐placing experiment, to reveal the practicability of our method.

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 .

Existing approaches have shown that, through carefully planning flight trajectories, images captured by Unmanned Aerial Vehicles (UAVs) can be used to reconstruct high-quality 3D models for real environments. These approaches greatly simplify and cut the cost of large-scale urban scene reconstruction. However, to properly capture height discontinuities in urban scenes, all state-of-the-art methods require prior knowledge on scene geometry and hence, additional prepossessing steps are needed before performing the actual image acquisition flights. To address this limitation and to make urban modeling techniques even more accessible, we present a real-time explore-and-reconstruct planning algorithm that does not require any prior knowledge for the scenes. Using only captured 2D images, we estimate 3D bounding boxes for buildings on-the-fly and use them to guide online path planning for both scene exploration and building observation. Experimental results demonstrate that the aerial paths planned by our algorithm in realtime for unknown environments support reconstructing 3D models with comparable qualities and lead to shorter flight air time.

We present TreePartNet , a neural network aimed at reconstructing tree geometry from point clouds obtained by scanning real trees. Our key idea is to learn a natural neural decomposition exploiting the assumption that a tree comprises locally cylindrical shapes. In particular, reconstruction is a two-step process. First, two networks are used to detect priors from the point clouds. One detects semantic branching points, and the other network is trained to learn a cylindrical representation of the branches. In the second step, we apply a neural merging module to reduce the cylindrical representation to a final set of generalized cylinders combined by branches. We demonstrate results of reconstructing realistic tree geometry for a variety of input models and with varying input point quality, e.g., noise, outliers, and incompleteness. We evaluate our approach extensively by using data from both synthetic and real trees and comparing it with alternative methods.

We present WireRoom , a computational framework for the intelligent design of abstract 3D wire art to depict a given 3D model. Our algorithm generates a set of 3D wire shapes from the 3D model with informative, visually pleasing, and concise structures. It is achieved by solving a dynamic travelling salesman problem on the surface of the 3D model with a multi-path expansion approach. We introduce a novel explorative computational design procedure by taking the generated wire shapes as candidates, avoiding manual design of the wire shape structure. We compare our algorithm with a baseline method and conduct a user study to investigate the usability of the framework and the quality of the produced wire shapes. The results of the comparison and user study confirm that our framework is effective for producing informative, visually pleasing, and concise wire shapes.

We introduce the first path-oriented drone trajectory planning algorithm, which performs continuous (i.e., dense ) image acquisition along an aerial path and explicitly factors path quality into an optimization along with scene reconstruction quality. Specifically, our method takes as input a rough 3D scene proxy and produces a drone trajectory and image capturing setup, which efficiently yields a high-quality reconstruction of the 3D scene based on three optimization objectives: one to maximize the amount of 3D scene information that can be acquired along the entirety of the trajectory, another to optimize the scene capturing efficiency by maximizing the scene information that can be acquired per unit length along the aerial path, and the last one to minimize the total turning angles along the aerial path, so as to reduce the number of sharp turns. Our search scheme is based on the rapidly-exploring random tree framework, resulting in a final trajectory as a single path through the search tree. Unlike state-of-the-art works, our joint optimization for view selection and path planning is performed in a single step. We comprehensively evaluate our method not only on benchmark virtual datasets as in existing works but also on several large-scale real urban scenes. We demonstrate that the continuous paths optimized by our method can effectively reduce onsite acquisition cost using drones, while achieving high-fidelity 3D reconstruction, compared to existing planning methods and oblique photography, a mature and popular industry solution.

We present a neural optimization model trained with reinforcement learning to solve the coordinate ordering problem for sets of star glyphs. Given a set of star glyphs associated to multiple class labels, we propose to use shape context descriptors to measure the perceptual distance between pairs of glyphs, and use the derived silhouette coefficient to measure the perception of class separability within the entire set. To find the optimal coordinate order for the given set, we train a neural network using reinforcement learning to reward orderings with high silhouette coefficients. The network consists of an encoder and a decoder with an attention mechanism. The encoder employs a recurrent neural network (RNN) to encode input shape and class information, while the decoder together with the attention mechanism employs another RNN to output a sequence with the new coordinate order. In addition, we introduce a neural network to efficiently estimate the similarity between shape context descriptors, which allows to speed up the computation of silhouette coefficients and thus the training of the axis ordering network. Two user studies demonstrate that the orders provided by our method are preferred by users for perceiving class separation. We tested our model on different settings to show its robustness and generalization abilities and demonstrate that it allows to order input sets with unseen data size, data dimension, or number of classes. We also demonstrate that our model can be adapted to coordinate ordering of other types of plots such as RadViz by replacing the proposed shape-aware silhouette coefficient with the corresponding quality metric to guide network training.

Specifying precise relationships among graphic elements is often a time-consuming process with traditional alignment tools. Automatic beautification of roughly designed layouts can provide a more efficient solution but often lead to undesired results due to ambiguity problems. To facilitate ambiguity resolution in layout beautification, we present a novel user interface for visualizing and editing inferred relationships through an automatic global layout beautification process. First, our interface provides a preview of the beautified layout with inferred constraints without directly modifying an input layout. In this way, the user can easily keep refining beautification results by interactively repositioning and/or resizing elements in the input layout. Second, we present a gestural interface for editing automatically inferred constraints by directly interacting with the visualized constraints via simple gestures. Our technique is applicable to both 2D and 3D global layout beautification, supported by efficient system implementation that provides instant user feedback. Our user study validates that our tool is capable of creating, editing, and refining layouts of graphic elements, and is significantly faster than the standard snap-dragging or command-based alignment tools for both 2D and 3D layout tasks.

Style transfer has been an important topic both in computer vision and graphics. Since the seminal work of Gatys et al. first demonstrates the power of stylization through optimization in the deep feature space, quite a few approaches have achieved real-time arbitrary style transfer with straightforward statistic matching techniques. In this work, our key observation is that only considering features in the input style image for the global deep feature statistic matching or local patch swap may not always ensure a satisfactory style transfer; see e.g., Figure 1. Instead, we propose a novel transfer framework, EFANet, that aims to jointly analyze and better align exchangeable features extracted from the content and style image pair. In this way, the style feature from the style image seeks for the best compatibility with the content information in the content image, leading to more structured stylization results. In addition, a new whitening loss is developed for purifying the computed content features and better fusion with styles in feature space. Qualitative and quantitative experiments demonstrate the advantages of our approach.

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.

Abstract Commonly used linear and nonlinear constitutive material models in deformation simulation contain many simplifications and only cover a tiny part of possible material behavior. In this work we propose a framework for learning customized models of deformable materials from example surface trajectories. The key idea is to iteratively improve a correction to a nominal model of the elastic and damping properties of the object, which allows new forward simulations with the learned correction to more accurately predict the behavior of a given soft object. Space‐time optimization is employed to identify gentle control forces with which we extract necessary data for model inference and to finally encapsulate the material correction into a compact parametric form. Furthermore, a patch based position constraint is proposed to tackle the challenge of handling incomplete and noisy observations arising in real‐world examples. We demonstrate the effectiveness of our method with a set of synthetic examples, as well with data captured from real world homogeneous elastic objects.

Semantic segmentation of images requires an understanding of appearances of objects and their spatial relationships in scenes. The fully convolutional network (FCN) has been successfully applied to recognize objects' appearances, which are represented with RGB channels. Images augmented with depth channels provide more understanding of the geometric information of the scene in an image. In this paper, we present a multiple-branch neural network to utilize depth information to assist in the semantic segmentation of images. Our approach splits the image into layers according to the "scene-scale". We introduce the context-aware receptive field (CARF), which provides better control of the relevant context information of learned features. Each branch of the network is equipped with CARF to adaptively aggregate the context information of image regions, leading to a more focused domain that is easier to learn. Furthermore, we propose a new zig-zag architecture to exchange information between the feature maps at different levels, augmented by the CARFs of the backbone network and decoder network. With the flexible information propagation allowed by our zig-zag network, we enrich the context information of feature maps for the segmentation. We show that the zig-zag network achieves state-of-the-art performances on several public datasets.

Context representations have been widely used to profit semantic image segmentation. The emergence of depth data provides additional information to construct more discriminating context representations. Depth data preserves the geometric relationship of objects in a scene, which is generally hard to be inferred from RGB images. While deep convolutional neural networks (CNNs) have been successful in solving semantic segmentation, we encounter the problem of optimizing CNN training for the informative context using depth data to enhance the segmentation accuracy. In this paper, we present a novel switchable context network (SCN) to facilitate semantic segmentation of RGB-D images. Depth data is used to identify objects existing in multiple image regions. The network analyzes the information in the image regions to identify different characteristics, which are then used selectively through switching network branches. With the content extracted from the inherent image structure, we are able to generate effective context representations that are aware of both image structures and object relationships, leading to a more coherent learning of semantic segmentation network. We demonstrate that our SCN outperforms state-of-the-art methods on two public datasets.

We introduce an inverse procedural modeling approach that learns L-system representations of pixel images with branching structures. Our fully automatic model generates a compact set of textual rewriting rules that describe the input. We use deep learning to discover atomic structures such as line segments or branchings. Orientation and scaling of these structures are determined and the detected structures are combined into a tree. The initial representation is analyzed, and repeating parts are encoded into a small grammar by using greedy optimization while the user can control the size of the detected rules. The output is an L-system that represents the input image as a simple text and a set of terminal symbols. We apply our approach to a variety of examples, demonstrate its robustness against noise and blur, and we show that it can detect user sketches and complex input structures.

We introduce a learning framework for automated floorplan generation which combines generative modeling using deep neural networks and user-in-the-loop designs to enable human users to provide sparse design constraints. Such constraints are represented by a layout graph. The core component of our learning framework is a deep neural network, Graph2Plan, which converts a layout graph, along with a building boundary, into a floorplan that fulfills both the layout and boundary constraints. Given an input building boundary, we allow a user to specify room counts and other layout constraints, which are used to retrieve a set of floorplans, with their associated layout graphs, from a database. For each retrieved layout graph, along with the input boundary, Graph2Plan first generates a corresponding raster floorplan image, and then a refined set of boxes representing the rooms. Graph2Plan is trained on RPLAN, a large-scale dataset consisting of 80K annotated floorplans. The network is mainly based on convolutional processing over both the layout graph, via a graph neural network (GNN), and the input building boundary, as well as the raster floorplan images, via conventional image convolution. We demonstrate the quality and versatility of our floorplan generation framework in terms of its ability to cater to different user inputs. We conduct both qualitative and quantitative evaluations, ablation studies, and comparisons with state-of-the-art approaches.

We introduce the transport-and-pack (TAP) problem, a frequently encountered instance of real-world packing, and develop a neural optimization solution based on reinforcement learning. Given an initial spatial configuration of boxes, we seek an efficient method to iteratively transport and pack the boxes compactly into a target container. Due to obstruction and accessibility constraints, our problem has to add a new search dimension, i.e., finding an optimal transport sequence , to the already immense search space for packing alone. Using a learning-based approach, a trained network can learn and encode solution patterns to guide the solution of new problem instances instead of executing an expensive online search. In our work, we represent the transport constraints using a precedence graph and train a neural network, coined TAP-Net, using reinforcement learning to reward efficient and stable packing. The network is built on an encoder-decoder architecture, where the encoder employs convolution layers to encode the box geometry and precedence graph and the decoder is a recurrent neural network (RNN) which inputs the current encoder output, as well as the current box packing state of the target container, and outputs the next box to pack, as well as its orientation. We train our network on randomly generated initial box configurations, without supervision , via policy gradients to learn optimal TAP policies to maximize packing efficiency and stability. We demonstrate the performance of TAP-Net on a variety of examples, evaluating the network through ablation studies and comparisons to baselines and alternative network designs. We also show that our network generalizes well to larger problem instances, when trained on small-sized inputs.

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.

With rapid development in UAV technologies, it is now possible to reconstruct large-scale outdoor scenes using only images captured by low-cost drones. The problem, however, becomes how to plan the aerial path for a drone to capture images so that two conflicting goals are optimized: maximizing the reconstruction quality and minimizing mid-air image acquisition effort. Existing approaches either resort to pre-defined dense and thus inefficient view sampling strategy, or plan the path adaptively but require two onsite flight passes and intensive computation in-between. Hence, using these methods to capture and reconstruct large-scale scenes can be tedious. In this paper, we present an adaptive aerial path planning algorithm that can be done before the site visit. Using only a 2D map and a satellite image of the to-be-reconstructed area, we first compute a coarse 2.5D model for the scene based on the relationship between buildings and their shadows. A novel Max-Min optimization is then proposed to select a minimal set of viewpoints that maximizes the reconstructability under the the same number of viewpoints. Experimental results on benchmark show that our planning approach can effectively reduce the number of viewpoints needed than the previous state-of-the-art method, while maintaining comparable reconstruction quality. Since no field computation or a second visit is needed, and the view number is also minimized, our approach significantly reduces the time required in the field as well as the off-line computation cost for multi-view stereo reconstruction, making it possible to reconstruct a large-scale urban scene in a short time with moderate effort.

We present a method for data sampling in scatterplots by jointly optimizing point selection for different views or classes. Our method uses space-filling curves (Z-order curves) that partition a point set into subsets that, when covered each by one sample, provide a sampling or coreset with good approximation guarantees in relation to the original point set. For scatterplot matrices with multiple views, different views provide different space-filling curves, leading to different partitions of the given point set. For multi-class scatterplots, the focus on either per-class distribution or global distribution provides two different partitions of the given point set that need to be considered in the selection of the coreset. For both cases, we convert the coreset selection problem into an Exact Cover Problem (ECP), and demonstrate with quantitative and qualitative evaluations that an approximate solution that solves the ECP efficiently is able to provide high-quality samplings.

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.

We introduce a mass-driven curve skeleton as a curve skeleton representation for 3D point cloud data. The mass-driven curve skeleton presents geometric properties and mass distribution of a curve skeleton simultaneously. The computation of the mass-driven curve skeleton is formulated as a minimization of Wasserstein distance, with an entropic regularization term, between mass distributions of point clouds and curve skeletons. Assuming that the mass of one sampling point should be transported to a line-like structure, a topology-aware rough curve skeleton is extracted via the optimal transport plan. A Dirichlet energy regularization term is then used to obtain a smooth curve skeleton via geometric optimization. Given that rough curve skeleton extraction does not depend on complete point clouds, our algorithm can be directly applied to curve skeleton extraction from incomplete point clouds. We demonstrate that a mass-driven curve skeleton can be directly applied to an unoriented raw point scan with significant noise, outliers and large areas of missing data. In comparison with state-of-the-art methods on curve skeleton extraction, the performance of the proposed mass-driven curve skeleton is more robust in terms of extracting a correct topology.

In recent decades, unmanned aerial vehicles (UAVs) have developed rapidly and been widely applied in many domains, including photography, reconstruction, monitoring, and search and rescue. In such applications, one key issue is path and view planning, which tells UAVs exactly where to fly and how to search. With specific consideration for three popular UAV applications (scene reconstruction, environment exploration, and aerial cinematography), we present a survey that should assist researchers in positioning and evaluating their works in the context of existing solutions. /Conclusions It should also help newcomers and practitioners in related fields quickly gain an overview of the vast literature. In addition to the current research status, we analyze and elaborate on advantages, disadvantages, and potential explorative trends for each application domain.

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.

Numerous valuable efforts have been devoted to achieving arbitrary style transfer since the seminal work of Gatys et al. However, existing state-of-the-art approaches often generate insufficiently stylized results under challenging cases. We believe a fundamental reason is that these approaches try to generate the stylized result in a single shot and hence fail to fully satisfy the constraints on semantic structures in the content images and style patterns in the style images. Inspired by the works on error-correction, instead, we propose a self-correcting model to predict what is wrong with the current stylization and refine it accordingly in an iterative manner. For each refinement, we transit the error features across both the spatial and scale domain and invert the processed features into a residual image, with a network we call Error Transition Network (ETNet). The proposed model improves over the state-of-the-art methods with better semantic structures and more adaptive style pattern details. Various qualitative and quantitative experiments show that the key concept of both progressive strategy and error-correction leads to better results. Code and models are available at https://github.com/zhijieW94/ETNet.

Abstract Point pattern synthesis is a fundamental tool with various applications in computer graphics. To synthesize a point pattern, some techniques have taken an example‐based approach, where the user provides a small exemplar of the target pattern. However, it remains challenging to synthesize patterns that faithfully capture the structures in the given exemplar. In this paper, we present a new example‐based point pattern synthesis method that preserves both local and non‐local structures present in the exemplar. Our method leverages recent neural texture synthesis techniques that have proven effective in synthesizing structured textures. The network that we present is end‐to‐end. It utilizes an irregular convolution layer, which converts a point pattern into a gridded feature map, to directly optimize point coordinates. The synthesis is then performed by matching inter‐ and intra‐correlations of the responses produced by subsequent convolution layers. We demonstrate that our point pattern synthesis qualitatively outperforms state‐of‐the‐art methods on challenging structured patterns, and enables various graphical applications, such as object placement in natural scenes, creative element patterns or realistic urban layouts in a 3D virtual environment.

Abstract We propose a novel approach to robot‐operated active understanding of unknown indoor scenes, based on online RGBD reconstruction with semantic segmentation. In our method, the exploratory robot scanning is both driven by and targeting at the recognition and segmentation of semantic objects from the scene. Our algorithm is built on top of a volumetric depth fusion framework and performs real‐time voxel‐based semantic labeling over the online reconstructed volume. The robot is guided by an online estimated discrete viewing score field (VSF) parameterized over the 3D space of 2D location and azimuth rotation. VSF stores for each grid the score of the corresponding view, which measures how much it reduces the uncertainty (entropy) of both geometric reconstruction and semantic labeling. Based on VSF, we select the next best views (NBV) as the target for each time step. We then jointly optimize the traverse path and camera trajectory between two adjacent NBVs, through maximizing the integral viewing score (information gain) along path and trajectory. Through extensive evaluation, we show that our method achieves efficient and accurate online scene parsing during exploratory scanning.

Active vision is inherently attention-driven: an agent actively selects views to attend in order to rapidly perform a vision task while improving its internal representation of the scene being observed. Inspired by the recent success of attention-based models in 2D vision tasks based on single RGB images, we address multi-view depth-based active object recognition using an attention mechanism, by use of an end-to-end recurrent 3D attentional network. The architecture takes advantage of a recurrent neural network to store and update an internal representation. Our model, trained with 3D shape datasets, is able to iteratively attend the best views targeting an object of interest for recognizing it. To realize 3D view selection, we derive a 3D spatial transformer network. It is differentiable, allowing training with backpropagation, and so achieving much faster convergence than the reinforcement learning employed by most existing attention-based models. Experiments show that our method, with only depth input, achieves state-of-the-art next-best-view performance both in terms of time taken and recognition accuracy.

We present a novel method to produce discernible image mosaics, with relatively large image tiles replaced by images drawn from a database, to resemble a target image. Compared to existing works on image mosaics, the novelty of our method is two-fold. Firstly, believing that the presence of visual edges in the final image mosaic strongly supports image perception, we develop an edge-aware photo retrieval scheme which emphasizes the preservation of visual edges in the target image. Secondly, unlike most previous works which apply a pre-determined partition to an input image, our image mosaics are composed of adaptive tiles, whose sizes are determined based on the available images in the database and the objective of maximizing resemblance to the target image. We show discernible image mosaics obtained by our method, using image collections of only moderate size. To evaluate our method, we conducted a user study to validate that the image mosaics generated present both globally and locally appropriate visual impressions to the human observers. Visual comparisons with existing techniques demonstrate the superiority of our method in terms of mosaic quality and perceptibility.

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 RPM-Net, a deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D point cloud shape. RPM-Net is a novel Recurrent Neural Network (RNN), composed of an encoder-decoder pair with interleaved Long Short-Term Memory (LSTM) components, which together predict a temporal sequence of pointwise displacements for the input point cloud. At the same time, the displacements allow the network to learn movable parts, resulting in a motion-based shape segmentation. Recursive applications of RPM-Net on the obtained parts can predict finer-level part motions, resulting in a hierarchical object segmentation. Furthermore, we develop a separate network to estimate part mobilities, e.g., per-part motion parameters, from the segmented motion sequence. Both networks learn deep predictive models from a training set that exemplifies a variety of mobilities for diverse objects. We show results of simultaneous motion and part predictions from synthetic and real scans of 3D objects exhibiting a variety of part mobilities, possibly involving multiple movable parts.

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 present a novel 3D model-guided interface for in-situ sketching on 3D planes. Our work is motivated by evolutionary design, where existing 3D objects form the basis for conceptual re-design or further design exploration. We contribute a novel workflow that exploits the geometry of an underlying 3D model to infer 3D planes on which 2D strokes drawn that are on and around the 3D model should be meaningfully projected. This provides users with the nearly modeless fluidity of a sketching interface, and is particularly useful for 3D sketching over planes that are not easily accessible or do not preexist. We also provide an additional set of tools, including sketching with explicit plane selection and model-aware canvas manipulation. Our system is evaluated with a user study, showing that our technique is easy to learn and effective for rapid sketching of product design variations around existing 3D models.

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.

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 The symmetrizable and converged Laplace–Beltrami operator ( ) is an indispensable tool for spectral geometrical analysis of point clouds. The , introduced by Liu et al. [LPG12] is guaranteed to be symmetrizable, but its convergence degrades when it is applied to models with sharp features. In this paper, we propose a novel , which is not only symmetrizable but also can handle the point‐sampled surface containing significant sharp features. By constructing the anisotropic Voronoi diagram in the local tangential space, the can be well constructed for any given point. To compute the area of anisotropic Voronoi cell, we introduce an efficient approximation by projecting the cell to the local tangent plane and have proved its convergence. We present numerical experiments that clearly demonstrate the robustness and efficiency of the proposed for point clouds that may contain noise, outliers, and non‐uniformities in thickness and spacing. Moreover, we can show that its spectrum is more accurate than the ones from existing for scan points or surfaces with sharp features.

Abstract Nowadays UAV filming is getting popular, more and more stunning aerial videos appearing online. Nonetheless, making a good uncut aerial video with only one‐long‐shot for the large‐scale outdoor scenes is still quite challenging, no many eye‐catching pieces available yet. It requires users to have both consummate drone controlling skill and good perception of filming aesthetics. If totally manual, the user has to simultaneously adjust the drone position and the mounted camera orientation during the whole flyby while trying to keep all operation changes executed smoothly. Recent research has proposed a number of planning tools for automatic or semi‐automatic aerial videography, however, most requires rather complex user inputs and heavy computations. In this paper, we propose a user‐friendly system designed to simplify the input and automatically generate continuous camera moves to capture compelling aerial videos that users prefer to see without any post cutting or editing. Assume a rough 2.5D scene model that includes all the regions of interest are available, users are only required to casually draw a single sketch on the 2D map. Our system will analyze this rough sketch input, compute the corresponding quality views in 3D safe flying zone, and then create a globally optimal camera trajectory passing through regions of user interest via solving a combinatorial problem. At end, we optimize the drone flying speed locally to make the resulting aerial videos more visually pleasing.

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.

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.

Humans can predict the functionality of an object even without any surroundings, since their knowledge and experience would allow them to "hallucinate" the interaction or usage scenarios involving the object. We develop predictive and generative deep convolutional neural networks to replicate this feat. Specifically, our work focuses on functionalities of man-made 3D objects characterized by human-object or object-object interactions. Our networks are trained on a database of scene contexts, called interaction contexts , each consisting of a central object and one or more surrounding objects, that represent object functionalities. Given a 3D object in isolation , our functional similarity network (fSIM-NET), a variation of the triplet network, is trained to predict the functionality of the object by inferring functionality-revealing interaction contexts. fSIM-NET is complemented by a generative network (iGEN-NET) and a segmentation network (iSEG-NET). iGEN-NET takes a single voxelized 3D object with a functionality label and synthesizes a voxelized surround, i.e., the interaction context which visually demonstrates the corresponding functionality. iSEG-NET further separates the interacting objects into different groups according to their interaction types.

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 study a new and elegant instance of geometric dissection of 2D shapes: reversible hinged dissection, which corresponds to a dual transform between two shapes where one of them can be dissected in its interior and then inverted inside-out , with hinges on the shape boundary, to reproduce the other shape, and vice versa. We call such a transform reversible inside-out transform or RIOT. Since it is rare for two shapes to possess even a rough RIOT, let alone an exact one, we develop both a RIOT construction algorithm and a quick filtering mechanism to pick, from a shape collection, potential shape pairs that are likely to possess the transform. Our construction algorithm is fully automatic. It computes an approximate RIOT between two given input 2D shapes, whose boundaries can undergo slight deformations, while the filtering scheme picks good inputs for the construction. Furthermore, we add properly designed hinges and connectors to the shape pieces and fabricate them using a 3D printer so that they can be played as an assembly puzzle. With many interesting and fun RIOT pairs constructed from shapes found online, we demonstrate that our method significantly expands the range of shapes to be considered for RIOT, a seemingly impossible shape transform, and offers a practical way to construct and physically realize these transforms.

To carry out autonomous 3D scanning and online reconstruction of unknown indoor scenes, one has to find a balance between global exploration of the entire scene and local scanning of the objects within it. In this work, we propose a novel approach, which provides object-aware guidance for autoscanning, for exploring, reconstructing, and understanding an unknown scene within one navigation pass. Our approach interleaves between object analysis to identify the next best object (NBO) for global exploration, and object-aware information gain analysis to plan the next best view (NBV) for local scanning. First, an objectness-based segmentation method is introduced to extract semantic objects from the current scene surface via a multi-class graph cuts minimization. Then, an object of interest (OOI) is identified as the NBO which the robot aims to visit and scan. The robot then conducts fine scanning on the OOI with views determined by the NBV strategy. When the OOI is recognized as a full object, it can be replaced by its most similar 3D model in a shape database. The algorithm iterates until all of the objects are recognized and reconstructed in the scene. Various experiments and comparisons have shown the feasibility of our proposed approach.

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.

Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing complete 3D shapes of transparent objects. Through positioning an object on a turntable, its silhouettes and light refraction paths under different viewing directions are captured. Then, starting from an initial rough model generated from space carving, our algorithm progressively optimizes the model under three constraints: surface and refraction normal consistency, surface projection and silhouette consistency, and surface smoothness. Experimental results on both synthetic and real objects demonstrate that our method can successfully recover the complex shapes of transparent objects and faithfully reproduce their light refraction properties.

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.

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.

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.

While crowdsourcing has been a cost and time efficient method to label massive samples, one critical issue is quality control, for which the key challenge is to infer the ground truth from noisy or even adversarial data by various users. A large class of crowdsourcing problems, such as those involving age, grade, level, or stage, have an ordinal structure in their labels. Based on a technique of sampling estimated label from the posterior distribution, we define a novel separating width among the labeled observations to characterize the quality of sampled labels, and develop an efficient algorithm to optimize it through solving multiple linear decision boundaries and adjusting prior distributions. Our algorithm is empirically evaluated on several real world datasets, and demonstrates its supremacy over state-of-the-art methods.

Abstract Global intrinsic symmetry detection of 3D shapes has received considerable attentions in recent years. However, unlike extrinsic symmetry that can be represented compactly as a combination of an orthogonal matrix and a translation vector, representing the global intrinsic symmetry itself is still challenging. Most previous works based on point‐to‐point representations of global intrinsic symmetries can only find reflectional symmetries, and are inadequate for describing the structure of a global intrinsic symmetry group. In this paper, we propose a novel group representation of global intrinsic symmetries, which describes each global intrinsic symmetry as a linear transformation of functional space on shapes. If the eigenfunctions of the Laplace‐Beltrami operator on shapes are chosen as the basis of functional space, the group representation has a block diagonal structure. We thus prove that the group representation of each symmetry can be uniquely determined from a small number of symmetric pairs of points under certain conditions, where the number of pairs is equal to the maximum multiplicity of eigenvalues of the Laplace‐Beltrami operator. Based on solid theoretical analysis, we propose an efficient global intrinsic symmetry detection method, which is the first one able to detect all reflectional and rotational global intrinsic symmetries with a clear group structure description. Experimental results demonstrate the effectiveness of our approach.

Abstract Flower blooming is a beautiful phenomenon in nature as flowers open in an intricate and complex manner whereas petals bend, stretch and twist under various deformations. Flower petals are typically thin structures arranged in tight configurations with heavy self‐occlusions. Thus, capturing and reconstructing spatially and temporally coherent sequences of blooming flowers is highly challenging. Early in the process only exterior petals are visible and thus interior parts will be completely missing in the captured data. Utilizing commercially available 3D scanners, we capture the visible parts of blooming flowers into a sequence of 3D point clouds. We reconstruct the flower geometry and deformation over time using a template‐based dynamic tracking algorithm. To track and model interior petals hidden in early stages of the blooming process, we employ an adaptively constrained optimization. Flower characteristics are exploited to track petals both forward and backward in time. Our methods allow us to faithfully reconstruct the flower blooming process of different species. In addition, we provide comparisons with state‐of‐the‐art physical simulation‐based approaches and evaluate our approach by using photos of captured real flowers.

Many interesting real-world textures are inhomogeneous and/or anisotropic. An inhomogeneous texture is one where various visual properties exhibit significant changes across the texture's spatial domain. Examples include perceptible changes in surface color, lighting, local texture pattern and/or its apparent scale, and weathering effects, which may vary abruptly, or in a continuous fashion. An anisotropic texture is one where the local patterns exhibit a preferred orientation, which also may vary across the spatial domain. While many example-based texture synthesis methods can be highly effective when synthesizing uniform (stationary) isotropic textures, synthesizing highly non-uniform textures, or ones with spatially varying orientation, is a considerably more challenging task, which so far has remained underexplored. In this paper, we propose a new method for automatic analysis and controlled synthesis of such textures. Given an input texture exemplar, our method generates a source guidance map comprising: (i) a scalar progression channel that attempts to capture the low frequency spatial changes in color, lighting, and local pattern combined, and (ii) a direction field that captures the local dominant orientation of the texture. Having augmented the texture exemplar with this guidance map, users can exercise better control over the synthesized result by providing easily specified target guidance maps, which are used to constrain the synthesis process.

Toward weather condition recognition, we emphasize the importance of regional cues in this paper and address a few important problems regarding appropriate representation, its differentiation among regions, and weather-condition feature construction. Our major contribution is, first, to construct a multi-class benchmark data set containing 65 000 images from six common categories for sunny, cloudy, rainy, snowy, haze, and thunder weather. This data set also benefits weather classification and attribute recognition. Second, we propose a deep learning framework named region selection and concurrency model (RSCM) to help discover regional properties and concurrency. We evaluate RSCM on our multi-class benchmark data and another public data set for weather recognition.

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.

We present a framework to distribute point samples with controlled spectral properties using a regular lattice of tiles with a single sample per tile. We employ a word-based identification scheme to identify individual tiles in the lattice. Our scheme is recursive, permitting tiles to be subdivided into smaller tiles that use the same set of IDs. The corresponding framework offers a very simple setup for optimization towards different spectral properties. Small lookup tables are sufficient to store all the information needed to produce different point sets. For blue noise with varying densities, we employ the bit-reversal principle to recursively traverse sub-tiles. Our framework is also capable of delivering multi-class blue noise samples. It is well-suited for different sampling scenarios in rendering, including area-light sampling (uniform and adaptive), and importance sampling. Other applications include stippling and distributing objects.

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.

We introduce a method for learning a model for the mobility of parts in 3D objects. Our method allows not only to understand the dynamic functionalities of one or more parts in a 3D object, but also to apply the mobility functions to static 3D models. Specifically, the learned part mobility model can predict mobilities for parts of a 3D object given in the form of a single static snapshot reflecting the spatial configuration of the object parts in 3D space, and transfer the mobility from relevant units in the training data. The training data consists of a set of mobility units of different motion types. Each unit is composed of a pair of 3D object parts (one moving and one reference part), along with usage examples consisting of a few snapshots capturing different motion states of the unit. Taking advantage of a linearity characteristic exhibited by most part motions in everyday objects, and utilizing a set of part-relation descriptors, we define a mapping from static snapshots to dynamic units. This mapping employs a motion-dependent snapshot-to-unit distance obtained via metric learning. We show that our learning scheme leads to accurate motion prediction from single static snapshots and allows proper motion transfer. We also demonstrate other applications such as motion-driven object detection and motion hierarchy construction.

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.

Abstract Digitally capturing vegetation using off‐the‐shelf scanners is a challenging problem. Plants typically exhibit large self‐occlusions and thin structures which cannot be properly scanned. Furthermore, plants are essentially dynamic, deforming over the time, which yield additional difficulties in the scanning process. In this paper, we present a novel technique for acquiring and modelling of plants and foliage. At the core of our method is an intrusive acquisition approach, which disassembles the plant into disjoint parts that can be accurately scanned and reconstructed offline. We use the reconstructed part meshes as 3D proxies for the reconstruction of the complete plant and devise a global‐to‐local non‐rigid registration technique that preserves specific plant characteristics. Our method is tested on plants of various styles, appearances and characteristics. Results show successful reconstructions with high accuracy with respect to the acquired data.

Abstract Consistent segmentation is to the center of many applications based on dynamic geometric data. Directly segmenting a raw 3D point cloud sequence is a challenging task due to the low data quality and large inter‐frame variation across the whole sequence. We propose alocal‐to‐globalapproach toco‐segmentpoint cloud sequences of articulated objects into near‐rigid moving parts. Our method starts from a per‐frame point clustering, derived from a robust voting‐based trajectory analysis. The local segments are then progressively propagated to the neighboring frames with a cut propagation operation, and further merged through all frames using a novelspace‐time segment groupingtechnqiue, leading to a globally consistent and compact segmentation of the entire articulated point cloud sequence. Such progressive propagating and merging, in both space and time dimensions, makes our co‐segmentation algorithm especially robust in handling noise, occlusions and pose/view variations that are usually associated with raw scan data.

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 introduce a co-analysis method which learns a functionality model for an object category, e.g., strollers or backpacks. Like previous works on functionality, we analyze object-to-object interactions and intra-object properties and relations. Differently from previous works, our model goes beyond providing a functionality-oriented descriptor for a single object; it prototypes the functionality of a category of 3D objects by co-analyzing typical interactions involving objects from the category. Furthermore, our co-analysis localizes the studied properties to the specific locations, or surface patches, that support specific functionalities, and then integrates the patch-level properties into a category functionality model. Thus our model focuses on the how , via common interactions, and where , via patch localization, of functionality analysis. Given a collection of 3D objects belonging to the same category, with each object provided within a scene context, our co-analysis yields a set of proto-patches , each of which is a patch prototype supporting a specific type of interaction, e.g., stroller handle held by hand. The learned category functionality model is composed of proto-patches, along with their pairwise relations, which together summarize the functional properties of all the patches that appear in the input object category. With the learned functionality models for various object categories serving as a knowledge base, we are able to form a functional understanding of an individual 3D object, without a scene context. With patch localization in the model, functionality-aware modeling , e.g, functional object enhancement and the creation of functional object hybrids, is made possible.

We present a novel technique that produces two-dimensional low-discrepancy (LD) blue noise point sets for sampling. Using one-dimensional binary van der Corput sequences, we construct two-dimensional LD point sets, and rearrange them to match a target spectral profile while preserving their low discrepancy. We store the rearrangement information in a compact lookup table that can be used to produce arbitrarily large point sets. We evaluate our technique and compare it to the state-of-the-art sampling approaches.

We introduce a 3D tree modeling technique that utilizes examples of real trees to enhance tree creation with realistic structures and fine-level details. In contrast to previous works that use smooth generalized cylinders to represent tree branches, our method generates realistic looking tree models with complex branching geometry by employing an exemplar database consisting of real-life trees reconstructed from scanned data. These trees are sliced into representative parts (denoted as tree-cuts), representing trunk logs and branching structures. In the modeling process, tree-cuts are positioned in space in an intuitive manner, serving as efficient proxies that guide the creation of the complete tree. Allometry rules are taken into account to ensure reasonable relations between adjacent branches. Realism is further enhanced by automatically transferring geometric textures from our database onto tree branches as well as by guided growing of foliage. Our results demonstrate the complexity and variety of trees that can be generated with our method within few minutes. We carry a user study to test the effectiveness of our modeling technique.

Feature learning for 3D shapes is challenging due to the lack of natural paramterization for 3D surface models. We adopt the multi-view depth image representation and propose Multi-View Deep Extreme Learning Machine (MVD-ELM) to achieve fast and quality projective feature learning for 3D shapes. In contrast to existing multi-view learning approaches, our method ensures the feature maps learned for different views are mutually dependent via shared weights and in each layer, their unprojections together form a valid 3D reconstruction of the input 3D shape through using normalized convolution kernels. These lead to a more accurate 3D feature learning as shown by the encouraging results in several applications. Moreover, the 3D reconstruction property enables clear visualization of the learned features, which further demonstrates the meaningfulness of our feature learning.

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.

Detailed scanning of indoor scenes is tedious for humans. We propose autonomous scene scanning by a robot to relieve humans from such a laborious task. In an autonomous setting, detailed scene acquisition is inevitably coupled with scene analysis at the required level of detail. We develop a framework for object-level scene reconstruction coupled with object-centric scene analysis. As a result, the autoscanning and reconstruction will be object-aware , guided by the object analysis. The analysis is, in turn, gradually improved with progressively increased object-wise data fidelity. In realizing such a framework, we drive the robot to execute an iterative analyze-and-validate algorithm which interleaves between object analysis and guided validations. The object analysis incorporates online learning into a robust graph-cut based segmentation framework, achieving a global update of object-level segmentation based on the knowledge gained from robot-operated local validation. Based on the current analysis, the robot performs proactive validation over the scene with physical push and scan refinement, aiming at reducing the uncertainty of both object-level segmentation and object-wise reconstruction. We propose a joint entropy to measure such uncertainty based on segmentation confidence and reconstruction quality, and formulate the selection of validation actions as a maximum information gain problem. The output of our system is a reconstructed scene with both object extraction and object-wise geometry fidelity.

We describe a novel technique for the fast production of large point sets with different spectral properties. In contrast to tile-based methods we use so-called AA Patterns: ornamental point sets obtained from quantization errors. These patterns have a discrete and structured number-theoretic nature, can be produced at very low costs, and possess an inherent structural indexing mechanism equivalent to those used in recursive tiling techniques. This allows us to generate, manipulate and store point sets very efficiently. The technique outperforms existing methods in speed, memory footprint, quality, and flexibility. This is demonstrated by a number of measurements and comparisons to existing point generation algorithms.

We present a data-driven method for deformation capture and modeling of general soft objects. We adopt an iterative framework that consists of one component for physics-based deformation tracking and another for spacetime optimization of deformation parameters. Low cost depth sensors are used for the deformation capture, and we do not require any force-displacement measurements, thus making the data capture a cheap and convenient process. We augment a state-of-the-art probabilistic tracking method to robustly handle noise, occlusions, fast movements and large deformations. The spacetime optimization aims to match the simulated trajectories with the tracked ones. The optimized deformation model is then used to boost the accuracy of the tracking results, which can in turn improve the deformation parameter estimation itself in later iterations. Numerical experiments demonstrate that the tracking and parameter optimization components complement each other nicely. Our spacetime optimization of the deformation model includes not only the material elasticity parameters and dynamic damping coefficients, but also the reference shape which can differ significantly from the static shape for soft objects. The resulting optimization problem is highly nonlinear in high dimensions, and challenging to solve with previous methods. We propose a novel splitting algorithm that alternates between reference shape optimization and deformation parameter estimation, and thus enables tailoring the optimization of each subproblem more efficiently and robustly. Our system enables realistic motion reconstruction as well as synthesis of virtual soft objects in response to user stimulation. Validation experiments show that our method not only is accurate, but also compares favorably to existing techniques. We also showcase the ability of our system with high quality animations generated from optimized deformation parameters for a variety of soft objects, such as live plants and fabricated models.

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 In this work, we introduce the ‘mobility‐tree’ construct for high‐level functional representation of complex 3D indoor scenes. In recent years, digital indoor scenes are becoming increasingly popular, consisting of detailed geometry and complex functionalities. These scenes often consist of objects that reoccur in various poses and interrelate with each other. In this work we analyse the reoccurrence of objects in the scene and automatically detect their functional mobilities. ‘Mobility’ analysis denotes the motion capabilities (i.e. degree of freedom) of an object and its subpart which typically relates to their indoor functionalities. We compute an object's mobility by analysing its spatial arrangement, repetitions and relations with other objects and store it in a ‘mobility‐tree’. Repetitive motions in the scenes are grouped in ‘mobility‐groups’, for which we develop a set of sophisticated controllers facilitating semantical high‐level editing operations. We show applications of our mobility analysis to interactive scene manipulation and reorganization, and present results for a variety of indoor scenes.

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.

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.

The evolution of 3D scanning technologies have revolutionized the way real-world object are digitally acquired. Nowadays, high-definition and high-speed scanners can capture even large scale scenes with very high accuracy. Nevertheless, the acquisition of complete 3D objects remains a bottleneck, requiring to carefully sample the whole object's surface, similar to a coverage process. Holes and undersampled regions are common in 3D scans of complex-shaped objects with self occlusions and hidden interiors. In this paper we introduce the novel paradigm of proactive scanning , in which the user actively modifies the scene while scanning it, in order to reveal and access occluded regions. We take a holistic approach and integrate the user interaction into the continuous scanning process. Our algorithm allows for dynamic modifications of the scene as part of a global 3D scanning process. We utilize a scan registration algorithm to compute motion trajectories and separate between user modifications and other motions such as (hand-held) camera movements and small deformations. Thus, we reconstruct together the static parts into a complete unified 3D model. We evaluate our technique by scanning and reconstructing 3D objects and scenes consisting of inaccessible regions such as interiors, entangled plants and clutter.

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 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 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.

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.