We introduce MaDCoW, a method for correcting marginal distortion of arbitrary objects in wide-angle photography. People often use wide-angle photography—it is the default in smartphone cameras—but very-wide-fields-of-view produce distorted object appearance in image margins. In our system, a user annotates straight lines and regions of interest. MaDCoW solves for a separate linear perspective projection for each region and then jointly solves for a distortion-minimizing projection for the whole photograph. We show that MaDCoW can produce good results in cases where previous methods yield visible distortions.

Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them impractical for real-world applications. We propose a novel approach for scalable and efficient data attribution. Our key idea is to distill a slow, unlearning-based attribution method to a feature embedding space for efficient retrieval of highly influential training images. During deployment, combined with efficient indexing and search methods, our method successfully finds highly influential images without running expensive attribution algorithms. We show extensive results on both medium-scale models trained on MSCOCO and large-scale Stable Diffusion models trained on LAION, demonstrating that our method can achieve better or competitive performance in a few seconds, faster than existing methods by 2,500x - 400,000x. Our work represents a meaningful step towards the large-scale application of data attribution methods on real-world models such as Stable Diffusion.

The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. Influence is defined such that, for a given output, if a model is retrained from scratch without the most influential images, the model would fail to reproduce the same output. Unfortunately, directly searching for these influential images is computationally infeasible, since it would require repeatedly retraining models from scratch. In our work, we propose an efficient data attribution method by simulating unlearning the synthesized image. We achieve this by increasing the training loss on the output image, without catastrophic forgetting of other, unrelated concepts. We then identify training images with significant loss deviations after the unlearning process and label these as influential. We evaluate our method with a computationally intensive but "gold-standard" retraining from scratch and demonstrate our method's advantages over previous methods.

Abstract Shape‐conveying line drawings generated from 3D models normally create closed regions in image space. These lines and regions can be stylized to mimic various artistic styles, but for complex objects, the extracted topology is unnecessarily dense, leading to unappealing and unnatural results under stylization. Prior works typically simplify line drawings without considering the regions between them, and lines and regions are stylized separately, then composited together, resulting in unintended inconsistencies. We present a method for joint simplification of lines and regions simultaneously that penalizes large changes to region structure, while keeping regions closed. This feature enables region stylization that remains consistent with the outline curves and underlying 3D geometry.

This article proposes a method for computing the visible occluding contours of subdivision surfaces. The article first introduces new theory for contour visibility of smooth surfaces. Necessary and sufficient conditions are introduced for when a sampled occluding contour is valid, that is, when it may be assigned consistent visibility. Previous methods do not guarantee these conditions, which helps explain why smooth contour visibility has been such a challenging problem in the past. The article then proposes an algorithm that, given a subdivision surface, finds sampled contours satisfying these conditions, and then generates a new triangle mesh matching the given occluding contours. The contours of the output triangle mesh may then be rendered with standard non-photorealistic rendering algorithms, using the mesh for visibility computation. The method can be applied to any triangle mesh, by treating it as the base mesh of a subdivision surface.

Abstract We present ZoomShop, a photographic composition editing tool for adjusting relative size, position, and foreshortening of scene elements. Given an image and corresponding depth map as input, ZoomShop combines a novel non‐linear camera model and a depth‐aware image warp to reproject and deform the image. Users can isolate objects by selecting depth ranges and adjust their scale and foreshortening, which controls the paths of the camera rays through the scene. Users can also select 2D image regions and translate them, which determines the objective function in the image warp optimization. We demonstrate that ZoomShop can be used to achieve useful compositional goals, such as making a distant object more prominent while preserving foreground scenery, or making objects both larger and closer together so they still fit in the frame.

This paper introduces a model for producing stylized line drawings from 3D shapes. The model takes a 3D shape and a viewpoint as input, and outputs a drawing with textured strokes, with variations in stroke thickness, deformation, and color learned from an artist’s style. The model is fully differentiable. We train its parameters from a single training drawing of another 3D shape. We show that, in contrast to previous image-based methods, the use of a geometric representation of 3D shape and 2D strokes allows the model to transfer important aspects of shape and texture style while preserving contours. Our method outputs the resulting drawing in a vector representation, enabling richer downstream analysis or editing in interactive applications. Our code and dataset are available at our project page: www.github.com/DifanLiu/NeuralStrokes

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences in the presence of noise and occlusions remains a challenge. For this purpose, we propose an expressive generative model in the form of a conditional variational autoencoder, which learns a distribution of the change in pose at each step of a motion sequence. Furthermore, we introduce a flexible optimization-based approach that leverages HuMoR as a motion prior to robustly estimate plausible pose and shape from ambiguous observations. Through extensive evaluations, we demonstrate that our model generalizes to diverse motions and body shapes after training on a large motion capture dataset, and enables motion reconstruction from multiple input modalities including 3D keypoints and RGB(-D) videos. See the project page at geometry.stanford.edu/projects/humor.

This paper introduces a motion retargeting method that preserves self-contacts and prevents interpenetration. Self-contacts, such as when hands touch each other or the torso or the head, are important attributes of human body language and dynamics, yet existing methods do not model or preserve these contacts. Likewise, interpenetration, such as a hand passing into the torso, are a typical artifact of motion estimation methods. The input to our method is a human motion sequence and a target skeleton and character geometry. The method identifies self-contacts and ground contacts in the input motion, and optimizes the motion to apply to the output skeleton, while preserving these contacts and reducing interpenetration. We introduce a novel geometry-conditioned recurrent network with an encoder-space optimization strategy that achieves efficient retargeting while satisfying contact constraints. In experiments, our results quantitatively outperform previous methods and we conduct a user study where our retargeted motions are rated as higher-quality than those produced by recent works. We also show our method generalizes to motion estimated from human videos where we improve over previous works that produce noticeable interpenetration.

Layout is important for graphic design and scene generation. We propose a novel Generative Adversarial Network, called LayoutGAN, that synthesizes layouts by modeling geometric relations of different types of 2D elements. The generator of LayoutGAN takes as input a set of randomly-placed 2D graphic elements, represented by vectors and uses self-attention modules to refine their labels and geometric parameters jointly to produce a realistic layout. Accurate alignment is critical for good layouts. We, thus, propose a novel differentiable wireframe rendering layer that maps the generated layout to a wireframe image, upon which a CNN-based discriminator is used to optimize the layouts in image space. We validate the effectiveness of LayoutGAN in various experiments including MNIST digit generation, document layout generation, clipart abstract scene generation, tangram graphic design, mobile app layout design, and webpage layout optimization from hand-drawn sketches.

This paper introduces a method for learning to generate line drawings from 3D models. Our architecture incorporates a differentiable module operating on geometric features of the 3D model, and an image-based module operating on view-based shape representations. At test time, geometric and view-based reasoning are combined with the help of a neural module to create a line drawing. The model is trained on a large number of crowdsourced comparisons of line drawings. Experiments demonstrate that our method achieves significant improvements in line drawing over the state-of-the-art when evaluated on standard benchmarks, resulting in drawings that are comparable to those produced by experienced human artists.

This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Component Analysis (PCA) applied either in latent space or feature space. Then, we show that a large number of interpretable controls can be defined by layer-wise perturbation along the principal directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches.

This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and applications. Previous methods for predicting saliency or visual importance are trained individually on specialized datasets, making them limited in application and leading to poor generalization on novel image classes, while requiring a user to know which model to apply to which input. UMSI is a deep learning-based model simultaneously trained on images from different design classes, including posters, infographics, mobile UIs, as well as natural images, and includes an automatic classification module to classify the input. This allows the model to work more effectively without requiring a user to label the input. We also introduce Imp1k, a new dataset of designs annotated with importance information. We demonstrate two new design interfaces that use importance prediction, including a tool for adjusting the relative importance of design elements, and a tool for reflowing designs to new aspect ratios while preserving visual importance.

It has long been hypothesized that perceptual ambiguities play an important role in aesthetic experience: A work with some ambiguity engages a viewer more than one that does not. However, current frameworks for testing this theory are limited by the availability of stimuli and data collection methods. This article presents an approach to measuring the perceptual ambiguity of a collection of images. Crowdworkers are asked to describe image content, after different viewing durations. Experiments are performed using images created with Generative Adversarial Networks, using the Artbreeder website. We show that text processing of viewer responses can provide a fine-grained way to measure and describe image ambiguities.

This paper introduces the problem of automatic font pairing. Font pairing is an important design task that is difficult for novices. Given a font selection for one part of a document (e.g., header), our goal is to recommend a font to be used in another part (e.g., body) such that the two fonts used together look visually pleasing. There are three main challenges in font pairing. First, this is a fine-grained problem, in which the subtle distinctions between fonts may be important. Second, rules and conventions of font pairing given by human experts are difficult to formalize. Third, font pairing is an asymmetric problem in that the roles played by header and body fonts are not interchangeable. To address these challenges, we propose automatic font pairing through learning visual relationships from large-scale human-generated font pairs. We introduce a new database for font pairing constructed from millions of PDF documents available on the Internet. We propose two font pairing algorithms: dual-space k-NN and asymmetric similarity metric learning (ASML). These two methods automatically learn fine-grained relationships from large-scale data. We also investigate several baseline methods based on the rules from professional designers. Experiments and user studies demonstrate the effectiveness of our proposed dataset and methods.

We propose a high-quality photo-to-pencil translation method with fine-grained control over the drawing style. This is a challenging task due to multiple stroke types (e.g., outline and shading), structural complexity of pencil shading (e.g., hatching), and the lack of aligned training data pairs. To address these challenges, we develop a two-branch model that learns separate filters for generating sketchy outlines and tonal shading from a collection of pencil drawings. We create training data pairs by extracting clean outlines and tonal illustrations from original pencil drawings using image filtering techniques, and we manually label the drawing styles. In addition, our model creates different pencil styles (e.g., line sketchiness and shading style) in a user-controllable manner. Experimental results on different types of pencil drawings show that the proposed algorithm performs favorably against existing methods in terms of quality, diversity and user evaluations.

A major concern for filmmakers creating 360° video is ensuring that the viewer does not miss important narrative elements because they are looking in the wrong direction. This paper introduces gated clips which do not play the video past a gate time until a filmmaker-defined viewer gaze condition is met, such as looking at a specific region of interest (ROI). Until the condition is met, we seamlessly loop video playback using view-dependent video textures, a new variant of standard video textures that adapt the looping behavior to the portion of the scene that is within the viewer's field of view. We use our desktop GUI to edit live action and computer animated 360° videos. In a user study with casual viewers, participants prefer our looping videos over the standard versions and are able to successfully see all of the looping videos' ROIs without fear of missing important narrative content.

Abstract Designing fonts and typefaces is a difficult process for both beginner and expert typographers. Existing workflows require the designer to create every glyph, while adhering to many loosely defined design suggestions to achieve an aesthetically appealing and coherent character set. This process can be significantly simplified by exploiting the similar structure character glyphs present across different fonts and the shared stylistic elements within the same font. To capture these correlations, we propose learning a stroke‐based font representation from a collection of existing typefaces. To enable this, we develop a stroke‐based geometric model for glyphs, a fitting procedure to reparametrize arbitrary fonts to our representation. We demonstrate the effectiveness of our model through a manifold learning technique that estimates a low‐dimensional font space. Our representation captures a wide range of everyday fonts with topological variations and naturally handles discrete and continuous variations, such as presence and absence of stylistic elements as well as slants and weights. We show that our learned representation can be used for iteratively improving fit quality, as well as exploratory style applications such as completing a font from a subset of observed glyphs, interpolating or adding and removing stylistic elements in existing fonts.

Graphic design tools provide powerful controls for expert-level design creation, but the options can often be overwhelming for novices. This paper proposes Context-Aware Asset Search tools that take the current state of the user's design into account, thereby providing search and selections that are compatible with the current design and better fit the user's needs. In particular, we focus on image search and color selection, two tasks that are central to design. We learn a model for compatibility of images and colors within a design, using crowdsourced data. We then use the learned model to rank image search results or color suggestions during design. We found counterintuitive behavior using conventional training with pairwise comparisons for image search, where models with and without compatibility performed similarly. We describe a data collection procedure that alleviates this problem. We show that our method outperforms baseline approaches in quantitative evaluation, and we also evaluate a prototype interactive design tool.

We present a method for adding parallax and real-time playback of 360° videos in Virtual Reality headsets. In current video players, the playback does not respond to translational head movement, which reduces the feeling of immersion, and causes motion sickness for some viewers. Given a 360° video and its corresponding depth (provided by current stereo 360° stitching algorithms), a naive image-based rendering approach would use the depth to generate a 3D mesh around the viewer, then translate it appropriately as the viewer moves their head. However, this approach breaks at depth discontinuities, showing visible distortions, whereas cutting the mesh at such discontinuities leads to ragged silhouettes and holes at disocclusions. We address these issues by improving the given initial depth map to yield cleaner, more natural silhouettes. We rely on a three-layer scene representation, made up of a foreground layer and two static background layers, to handle disocclusions by propagating information from multiple frames for the first background layer, and then inpainting for the second one. Our system works with input from many of today's most popular 360° stereo capture devices (e.g., Yi Halo or GoPro Odyssey), and works well even if the original video does not provide depth information. Our user studies confirm that our method provides a more compelling viewing experience than without parallax, increasing immersion while reducing discomfort and nausea.

Applications for viewing and editing 360° video often render user interface (UI) elements on top of the video. For stereoscopic video, in which the perceived depth varies over the image, the perceived depth of the video can conflict with that of the UI elements, creating discomfort and making it hard to shift focus. To address this problem, we explore two new techniques that adjust the UI rendering based on the video content. The first technique dynamically adjusts the perceived depth of the UI to avoid depth conflict, and the second blurs the video in a halo around the UI. We conduct a user study to assess the effectiveness of these techniques in two stereoscopic VR video tasks: video watching with subtitles, and video search.

Creative professionals are creating Virtual Reality (VR) experiences today by capturing spherical videos, but video editing is still done primarily in traditional 2D desktop GUI applications such as Premiere. These interfaces provide limited capabilities for previewing content in a VR headset or for directly manipulating the spherical video in an intuitive way. As a result, editors must alternate between editing on the desktop and previewing in the headset, which is tedious and interrupts the creative process. We demonstrate an application that enables a user to directly edit spherical video while fully immersed in a VR headset. We first interviewed professional VR filmmakers to understand current practice and derived a suitable workflow for in-headset VR video editing. We then developed a prototype system implementing this new workflow. Our system is built upon a familiar timeline design, but is enhanced with custom widgets to enable intuitive editing of spherical video inside the headset. We conducted an expert review study and found that with our prototype, experts were able to edit videos entirely within the headset. Experts also found our interface and widgets useful, providing intuitive controls for their editing needs.

Neural Style Transfer has shown very exciting results enabling new forms of image manipulation. Here we extend the existing method to introduce control over spatial location, colour information and across spatial scale. We demonstrate how this enhances the method by allowing high-resolution controlled stylisation and helps to alleviate common failure cases such as applying ground textures to sky regions. Furthermore, by decomposing style into these perceptual factors we enable the combination of style information from multiple sources to generate new, perceptually appealing styles from existing ones. We also describe how these methods can be used to more efficiently produce large size, high-quality stylisation. Finally we show how the introduced control measures can be applied in recent methods for Fast Neural Style Transfer.

Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photographs. Artwork produced by people is not constrained to mimic the physical world, making it more challenging for machines to recognize.,,This work is a step toward teaching machines how to categorize images in ways that are valuable to humans. First, we collect a large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists. We annotate Behance imagery with rich attribute labels for content, emotions, and artistic media. Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of existing object classifiers, and for the study of visual domain adaptation. We believe our Behance Artistic Media dataset will be a good starting point for researchers wishing to study artistic imagery and relevant problems. This dataset can be found at https://bam-dataset.org/.

Knowing where people look and click on visual designs can provide clues about how the designs are perceived, and where the most important or relevant content lies. The most important content of a visual design can be used for effective summarization or to facilitate retrieval from a database. We present automated models that predict the relative importance of different elements in data visualizations and graphic designs. Our models are neural networks trained on human clicks and importance annotations on hundreds of designs. We collected a new dataset of crowdsourced importance, and analyzed the predictions of our models with respect to ground truth importance and human eye movements. We demonstrate how such predictions of importance can be used for automatic design retargeting and thumbnailing. User studies with hundreds of MTurk participants validate that, with limited post-processing, our importance-driven applications are on par with, or outperform, current state-of-the-art methods, including natural image saliency. We also provide a demonstration of how our importance predictions can be built into interactive design tools to offer immediate feedback during the design process.

Collaborative review and feedback is an important part of conventional filmmaking and now Virtual Reality (VR) video production as well. However, conventional collaborative review practices do not easily translate to VR video because VR video is normally viewed in a headset, which makes it difficult to align gaze, share context, and take notes. This paper presents CollaVR, an application that enables multiple users to review a VR video together while wearing headsets. We interviewed VR video professionals to distill key considerations in reviewing VR video. Based on these insights, we developed a set of networked tools that enable filmmakers to collaborate and review video in real-time. We conducted a preliminary expert study to solicit feedback from VR video professionals about our system and assess their usage of the system with and without collaboration features.

We propose a method for converting geometric shapes into hierarchically segmented parts with part labels. Our key idea is to train category-specific models from the scene graphs and part names that accompany 3D shapes in public repositories. These freely-available annotations represent an enormous, untapped source of information on geometry. However, because the models and corresponding scene graphs are created by a wide range of modelers with different levels of expertise, modeling tools, and objectives, these models have very inconsistent segmentations and hierarchies with sparse and noisy textual tags. Our method involves two analysis steps. First, we perform a joint optimization to simultaneously cluster and label parts in the database while also inferring a canonical tag dictionary and part hierarchy. We then use this labeled data to train a method for hierarchical segmentation and labeling of new 3D shapes. We demonstrate that our method can mine complex information, detecting hierarchies in man-made objects and their constituent parts, obtaining finer scale details than existing alternatives. We also show that, by performing domain transfer using a few supervised examples, our technique outperforms fully-supervised techniques that require hundreds of manually-labeled models.

Abstract Portraiture is a major art form in both photography and painting. In most instances, artists seek to make the subject stand out from its surrounding, for instance, by making it brighter or sharper. In the digital world, similar effects can be achieved by processing a portrait image with photographic or painterly filters that adapt to the semantics of the image. While many successful user‐guided methods exist to delineate the subject, fully automatic techniques are lacking and yield unsatisfactory results. Our paper first addresses this problem by introducing a new automatic segmentation algorithm dedicated to portraits. We then build upon this result and describe several portrait filters that exploit our automatic segmentation algorithm to generate high‐quality portraits.

Creating graphic designs can be challenging for novice users. This paper presents DesignScape, a system which aids the design process by making interactive layout suggestions, i.e., changes in the position, scale, and alignment of elements. The system uses two distinct but complementary types of suggestions: refinement suggestions, which improve the current layout, and brainstorming suggestions, which change the style. We investigate two interfaces for interacting with suggestions. First, we develop a suggestive interface, where suggestions are previewed and can be accepted. Second, we develop an adaptive interface where elements move automatically to improve the layout. We compare both interfaces with a baseline without suggestions, and show that for novice designers, both interfaces produce significantly better layouts, as evaluated by other novices.

Event sequence data analysis is common in many domains, including web and software development, transportation, and medical care. Few have investigated visualization techniques for comparative analysis of multiple event sequence datasets. Grounded in the real-world characteristics of web clickstream data, we explore visualization techniques for comparison of two clickstream datasets collected on different days or from users with different demographics. Through iterative design with web analysts, we designed MatrixWave, a matrix-based representation that allows analysts to get an overview of differences in traffic patterns and interactively explore paths through the website. We use color to encode differences and size to offer context over traffic volume. User feedback on MatrixWave is positive. Our study participants made fewer errors with MatrixWave and preferred it over the more familiar Sankey diagram.

There is often more than one way to select tonal adjustment-for a photograph, and different individuals may prefer different adjustments. However, selecting good adjustments is challenging. This paper describes a method to predict whether a given tonal rendition is acceptable for a photograph, which we use to characterize its range of acceptable adjustments. We gathered a dataset of image “acceptability” over brightness and contrast adjustments. We find that unacceptable renditions can be explained in terms of overexposure, under-exposure, and low contrast. Based on this observation, we propose a machine-learning algorithm to assess whether an adjusted photograph looks acceptable. We show that our algorithm can differentiate unsightly renditions from reasonable ones. Finally, we describe proof-of-concept applications that use our algorithm to guide the exploration of the possible tonal renditions of a photograph.

We propose an efficient optimization algorithm to select a subset of training data as the inducing set for sparse Gaussian process regression. Previous methods either use different objective functions for inducing set and hyperparameter selection, or else optimize the inducing set by gradient-based continuous optimization. The former approaches are harder to interpret and suboptimal, whereas the latter cannot be applied to discrete input domains or to kernel functions that are not differentiable with respect to the input. The algorithm proposed in this work estimates an inducing set and the hyperparameters using a single objective. It can be used to optimize either the marginal likelihood or a variational free energy. Space and time complexity are linear in training set size, and the algorithm can be applied to large regression problems on discrete or continuous domains. Empirical evaluation shows state-of-art performance in discrete cases, competitive prediction results as well as a favorable trade-off between training and test time in continuous cases.

This paper presents a method for learning to predict the stylistic compatibility between 3D furniture models from different object classes: e.g., how well does this chair go with that table? To do this, we collect relative assessments of style compatibility using crowdsourcing. We then compute geometric features for each 3D model and learn a mapping of them into a space where Euclidean distances represent style incompatibility. Motivated by the geometric subtleties of style, we introduce part-aware geometric feature vectors that characterize the shapes of different parts of an object separately. Motivated by the need to compute style compatibility between different object classes, we introduce a method to learn object class-specific mappings from geometric features to a shared feature space. During experiments with these methods, we find that they are effective at predicting style compatibility agreed upon by people. We find in user studies that the learned compatibility metric is useful for novel interactive tools that: 1) retrieve stylistically compatible models for a query, 2) suggest a piece of furniture for an existing scene, and 3) help guide an interactive 3D modeler towards scenes with compatible furniture.

This paper presents a method for acquiring dense nonrigid shape and deformation from a single monocular depth sensor. We focus on modeling the human hand, and assume that a single rough template model is available. We combine and extend existing work on model-based tracking, subdivision surface fitting, and mesh deformation to acquire detailed hand models from as few as 15 frames of depth data. We propose an objective that measures the error of fit between each sampled data point and a continuous model surface defined by a rigged control mesh, and uses as-rigid-as-possible (ARAP) regularizers to cleanly separate the model and template geometries. A key contribution is our use of a smooth model based on subdivision surfaces that allows simultaneous optimization over both correspondences and model parameters. This avoids the use of iterated closest point (ICP) algorithms which often lead to slow convergence. Automatic initialization is obtained using a regression forest trained to infer approximate correspondences. Experiments show that the resulting meshes model the user's hand shape more accurately than just adapting the shape parameters of the skeleton, and that the retargeted skeleton accurately models the user's articulations. We investigate the effect of various modeling choices, and show the benefits of using subdivision surfaces and ARAP regularization.

We present PortraitSketch, an interactive drawing system that helps novices create pleasing, recognizable face sketches without requiring prior artistic training. As the user traces over a source portrait photograph, PortraitSketch automatically adjusts the geometry and stroke parameters (thickness, opacity, etc.) to improve the aesthetic quality of the sketch. We present algorithms for adjusting both outlines and shading strokes based on important features of the underlying source image. In contrast to automatic stylization systems, PortraitSketch is designed to encourage a sense of ownership and accomplishment in the user. To this end, all adjustments are performed in real-time, and the user ends up directly drawing all strokes on the canvas. The findings from our user study suggest that users prefer drawing with some automatic assistance, thereby producing better drawings, and that assistance does not decrease the perceived level of involvement in the creative process.

Abstract Synthesizing controllers for rotational movements in feature space is an open research problem and is particularly challenging because of the need to precisely regulate the character's global orientation, angular momentum and inertia. This paper presents feature‐based controllers for a wide variety of rotational movements, including cartwheels, dives and flips. We show that the controllers can be made robust to large external disturbances by using a time‐invariant control scheme. The generality of the control laws is demonstrated by providing examples of the flip controller with different apexes, the diving controller with different heights and styles, the cartwheel controller with different speeds and straddle widths, etc. The controllers do not rely on any input motion or offline optimization.

This article introduces a method for accurately computing the visible contours of a smooth 3D surface for stylization. This is a surprisingly difficult problem, and previous methods are prone to topological errors, such as gaps in the outline. Our approach is to generate, for each viewpoint, a new triangle mesh with contours that are topologically equivalent and geometrically close to those of the original smooth surface. The contours of the mesh can then be rendered with exact visibility. The core of the approach is Contour Consistency, a way to prove topological equivalence between the contours of two surfaces. Producing a surface tessellation that satisfies this property is itself challenging; to this end, we introduce a type of triangle that ensures consistency at the contour. We then introduce an iterative mesh generation procedure, based on these ideas. This procedure does not fully guarantee consistency, but errors are not noticeable in our experiments. Our algorithm can operate on any smooth input surface representation; we use Catmull-Clark subdivision surfaces in our implementation. We demonstrate results computing contours of complex 3D objects, on which our method eliminates the contour artifacts of other methods.

This paper presents a method for measuring the similarity in style between two pieces of vector art, independent of content. Similarity is measured by the differences between four types of features: color, shading, texture, and stroke. Feature weightings are learned from crowdsourced experiments. This perceptual similarity enables style-based search. Using our style-based search feature, we demonstrate an application that allows users to create stylistically-coherent clip art mash-ups.

This paper presents interfaces for exploring large collections of fonts for design tasks. Existing interfaces typically list fonts in a long, alphabetically-sorted menu that can be challenging and frustrating to explore. We instead propose three interfaces for font selection. First, we organize fonts using high-level descriptive attributes, such as "dramatic" or "legible." Second, we organize fonts in a tree-based hierarchical menu based on perceptual similarity. Third, we display fonts that are most similar to a user's currently-selected font. These tools are complementary; a user may search for "graceful" fonts, select a reasonable one, and then refine the results from a list of fonts similar to the selection. To enable these tools, we use crowdsourcing to gather font attribute data, and then train models to predict attribute values for new fonts. We use attributes to help learn a font similarity metric using crowdsourced comparisons. We evaluate the interfaces against a conventional list interface and find that our interfaces are preferred to the baseline. Our interfaces also produce better results in two real-world tasks: finding the nearest match to a target font, and font selection for graphic designs.

This paper presents an approach for automatically creating graphic design layouts using a new energy-based model derived from design principles. The model includes several new algorithms for analyzing graphic designs, including the prediction of perceived importance, alignment detection, and hierarchical segmentation. Given the model, we use optimization to synthesize new layouts for a variety of single-page graphic designs. Model parameters are learned with Nonlinear Inverse Optimization (NIO) from a small number of example layouts. To demonstrate our approach, we show results for applications including generating design layouts in various styles, retargeting designs to new sizes, and improving existing designs. We also compare our automatic results with designs created using crowdsourcing and show that our approach performs slightly better than novice designers.

Traditionally, human pose estimation algorithms could be classified into generative [2] and discriminative [4] approaches. Generative approaches model the likelihood of the observations given a pose estimate, however, they are susceptible to local minima and thus require good initial pose estimates. Discriminative approaches learn a direct mapping from image features to pose space from training data, however, they struggle to generalize to unseen poses. Building on previous work [3], Taylor et al. [5] bypass some of these limitations using a hybrid-approach that discriminatively predicts, for each pixel in a depth image, a corresponding point on the surface of a humanoid mesh model. This mesh model is then robustly fit to the resulting set of correspondences using local optimization. Surprisingly though, these correspondences are actually inferred using a random forest whose structure was trained using a classification objective that arbitrarily equates target model points belonging to the same predefined body part [3]. In this paper, we address Taylor et al.’s use of this proxy classification objective by proposing Metric Space Information Gain (MSIG), a replacement objective function for training a random forest to directly minimize the uncertainty over the target model points, naturally encoding the correlation between these points as a function of the geodesic distance. To this end, we view the surface of the model U as a metric space (U,dU) defined by the geodesic distance metric dU (see first panel of Figure 1). The natural objective function to minimize the uncertainty in the resulting true distributions that result from a split function s in such a space, is the information gain I(s) [1]. This is generally approximated using an empirical distribution Q = {ui} ⊆U drawn from the true unsplit distribution pU as I(s)≈ I(s;Q) = Ĥ(Q)− ∑ i∈{L,R} |Qi| |Q| Ĥ(Qi), (1)

We propose an efficient discrete optimization algorithm for selecting a subset of training data to induce sparsity for Gaussian process regression. The algorithm estimates this inducing set and the hyperparameters using a single objective, either the marginal likelihood or a variational free energy. The space and time complexity are linear in the training set size, and the algorithm can be applied to large regression problems on discrete or continuous domains. Empirical evaluation shows state-of-art performance in the discrete case and competitive results in the continuous case.

This paper presents the first method for full-body trajectory optimization of physics-based human motion that does not rely on motion capture, specified key-poses, or periodic motion. Optimization is performed using a small set of simple goals, for example, one hand should be on the ground, or the center-of-mass should be above a particular height. These objectives are applied to short spacetime windows which can be composed to express goals over an entire animation. Specific contact locations needed to achieve objectives are not required by our method. We show that the method can synthesize many different kinds of movement, including walking, hand walking, breakdancing, flips, and crawling. Most of these movements have never been previously synthesized by physics-based methods.

Imagining what a proposed home remodel might look like without actually performing it is challenging. We present an image-based remodeling methodology that allows real-time photorealistic visualization during both the modeling and remodeling process of a home interior. Large-scale edits, like removing a wall or enlarging a window, are performed easily and in real time, with realistic results. Our interface supports the creation of concise, parameterized, and constrained geometry, as well as remodeling directly from within the photographs. Real-time texturing of modified geometry is made possible by precomputing view-dependent textures for all faces that are potentially visible to each original camera viewpoint, blending multiple viewpoints and hole-filling when necessary. The resulting textures are stored and accessed efficiently enabling intuitive real-time realistic visualization, modeling, and editing of the building interior.

This article presents an algorithm for learning hatching styles from line drawings. An artist draws a single hatching illustration of a 3D object. Her strokes are analyzed to extract the following per-pixel properties: hatching level (hatching, cross-hatching, or no strokes), stroke orientation, spacing, intensity, length, and thickness. A mapping is learned from input geometric, contextual, and shading features of the 3D object to these hatching properties, using classification, regression, and clustering techniques. Then, a new illustration can be generated in the artist's style, as follows. First, given a new view of a 3D object, the learned mapping is applied to synthesize target stroke properties for each pixel. A new illustration is then generated by synthesizing hatching strokes according to the target properties.

This paper presents an interactive system for creating painterly animation from video sequences. Previous approaches to painterly animation typically emphasize either purely automatic stroke synthesis or purely manual stroke key framing. Our system supports a spectrum of interaction between these two approaches which allows the user more direct control over stroke synthesis. We introduce an approach for controlling the results of painterly animation: keyframed Control Strokes can affect automatic stroke's placement, orientation, movement, and color. Furthermore, we introduce a new automatic synthesis algorithm that traces strokes through a video sequence in a greedy manner, but, instead of a vector field, uses an objective function to guide placement. This allows the method to capture fine details, respect region boundaries, and achieve greater temporal coherence than previous methods. All editing is performed with a WYSIWYG interface where the user can directly refine the animation. We demonstrate a variety of examples using both automatic and user-guided results, with a variety of styles and source videos.

This paper studies color compatibility theories using large datasets, and develops new tools for choosing colors. There are three parts to this work. First, using on-line datasets, we test new and existing theories of human color preferences. For example, we test whether certain hues or hue templates may be preferred by viewers. Second, we learn quantitative models that score the quality of a five-color set of colors, called a color theme . Such models can be used to rate the quality of a new color theme. Third, we demonstrate simple proto-types that apply a learned model to tasks in color design, including improving existing themes and extracting themes from images.

This paper describes a photometric stereo method designed for surfaces with spatially-varying BRDFs, including surfaces with both varying diffuse and specular properties. Our optimization-based method builds on the observation that most objects are composed of a small number of fundamental materials by constraining each pixel to be representable by a combination of at most two such materials. This approach recovers not only the shape but also material BRDFs and weight maps, yielding accurate rerenderings under novel lighting conditions for a wide variety of objects. We demonstrate examples of interactive editing operations made possible by our approach.

This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes. An objective function is formulated as a Conditional Random Field model, with terms assessing the consistency of faces with labels, and terms between labels of neighboring faces. The objective function is learned from a collection of labeled training meshes. The algorithm uses hundreds of geometric and contextual label features and learns different types of segmentations for different tasks, without requiring manual parameter tuning. Our algorithm achieves a significant improvement in results over the state-of-the-art when evaluated on the Princeton Segmentation Benchmark, often producing segmentations and labelings comparable to those produced by humans.

This paper introduces an approach to control of physics-based characters based on high-level features of movement, such as center-of-mass, angular momentum, and end-effectors. Objective terms are used to control each feature, and are combined by a prioritization algorithm. We show how locomotion can be expressed in terms of a small number of features that control balance and end-effectors. This approach is used to build controllers for human balancing, standing jump, and walking. These controllers provide numerous benefits: human-like qualities such as arm-swing, heel-off, and hip-shoulder counter-rotation emerge automatically during walking; controllers are robust to changes in body parameters; control parameters and goals may be modified at run-time; control parameters apply to intuitive properties such as center-of-mass height; and controllers may be mapped onto entirely new bipeds with different topology and mass distribution, without modifications to the controller itself. No motion capture or off-line optimization process is used.

This paper presents a physics-based locomotion controller based on online planning. At each time-step, a planner optimizes locomotion over multiple phases of gait. Stance dynamics are modeled using a simplified Spring-Load Inverted (SLIP) model, while flight dynamics are modeled using projectile motion equations. Full-body control at each instant is optimized to match the instantaneous plan values, while also maintaining balance. Different types of gaits, including walking, running, and jumping, emerge automatically, as do transitions between different gaits. The controllers can traverse challenging terrain and withstand large external disturbances, while following high-level user commands at interactive rates.

We introduce methods for optimizing physics-based walking controllers for robustness to uncertainty. Many unknown factors, such as external forces, control torques, and user control inputs, cannot be known in advance and must be treated as uncertain. These variables are represented with probability distributions, and a return function scores the desirability of a single motion. Controller optimization entails maximizing the expected value of the return, which is computed by Monte Carlo methods. We demonstrate examples with different sources of uncertainty and task constraints. Optimizing control strategies under uncertainty increases robustness and produces natural variations in style.

This paper presents a method for estimating geographic location for sequences of time-stamped photographs. A prior distribution over travel describes the likelihood of traveling from one location to another during a given time interval. This distribution is based on a training database of 6 million photographs from Flickr.com. An image likelihood for each location is defined by matching a test photograph against the training database. Inferring location for images in a test sequence is then performed using the Forward-Backward algorithm, and the model can be adapted to individual users as well. Using temporal constraints allows our method to geolocate images without recognizable landmarks, and images with no geographic cues whatsoever. This method achieves a substantial performance improvement over the best-available baseline, and geolocates some users' images with near-perfect accuracy.

We introduce an optimization framework called prioritized optimization control, in which a nested sequence of objectives are optimized so as not to conflict with higher-priority objectives. We focus on the case of quadratic objectives and derive an efficient recursive solver for this case. We show how task-space control can be formulated in this framework, and demonstrate the technique on three sample control problems. The proposed formulation supports acceleration, torque, and bilateral force constraints, while simplifying reasoning about task-space control. This scheme unifies prioritized task-space and optimization-based control. Our method computes control torques for all presented examples in real-time.

This article presents a method for real-time line drawing of deforming objects. Object-space line drawing algorithms for many types of curves, including suggestive contours, highlights, ridges, and valleys, rely on surface curvature and curvature derivatives. Unfortunately, these curvatures and their derivatives cannot be computed in real-time for animated, deforming objects. In a preprocessing step, our method learns the mapping from a low-dimensional set of animation parameters (e.g., joint angles) to surface curvatures for a deforming 3D mesh. The learned model can then accurately and efficiently predict curvatures and their derivatives, enabling real-time object-space rendering of suggestive contours and other such curves. This represents an order-of-magnitude speedup over the fastest existing algorithm capable of estimating curvatures and their derivatives accurately enough for many different types of line drawings. The learned model can generalize to novel animation sequences and is also very compact, typically requiring a few megabytes of storage at runtime. We demonstrate our method for various types of animated objects, including skeleton-based characters, cloth simulation, and blend-shape facial animation, using a variety of nonphotorealistic rendering styles. An important component of our system is the use of dimensionality reduction for differential mesh data. We show that Independent Component Analysis (ICA) yields localized basis functions, and gives superior generalization performance to that of Principal Component Analysis (PCA).

This paper describes a method for optimizing the parameters of a physics-based controller for full-body, 3D walking. A modified version of the SIMBICON controller [Yin et al. 2007] is optimized for characters of varying body shape, walking speed and step length. The objective function includes terms for power minimization, angular momentum minimization, and minimal head motion, among others. Together these terms produce a number of important features of natural walking, including active toe-off, near-passive knee swing, and leg extension during swing. We explain the specific form of our objective criteria, and show the importance of each term to walking style. We demonstrate optimized controllers for walking with different speeds, variation in body shape, and in ground slope.

This paper describes methods for recovering time-varying shape and motion of non-rigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talking person, we would like to estimate the 3D shape of the face at each instant, and learn a model of facial deformation. Time-varying shape is modeled as a rigid transformation combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deformations are allowed, and thus additional assumptions about deformations are required. We first suggest restricting shapes to lie within a low-dimensional subspace, and describe estimation algorithms. However, this restriction alone is insufficient to constrain reconstruction. To address these problems, we propose a reconstruction method using a Probabilistic Principal Components Analysis (PPCA) shape model, and an estimation algorithm that simultaneously estimates 3D shape and motion for each instant, learns the PPCA model parameters, and robustly fills-in missing data points. We then extend the model to model temporal dynamics in object shape, allowing the algorithm to robustly handle severe cases of missing data.

We introduce Gaussian process dynamical models (GPDM) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensionalmotion capture data. A GPDM is a latent variable model. It comprises a low-dimensional latent space with associated dynamics, and a map from the latent space to an observation space. We marginalize out the model parameters in closed-form, using Gaussian process priors for both the dynamics and the observation mappings. This results in a non-parametric model for dynamical systems that accounts for uncertainty in the model. We demonstrate the approach, and compare four learning algorithms on human motion capture data in which each pose is 50-dimensional. Despite the use of small data sets, the GPDM learns an effective representation of the nonlinear dynamics in these spaces.

In the above titled paper (ibid., vol. 30, no. 2, pp. 283-298, Feb 08), two figures were misprinted. The correct figures are presented here.

We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bipedal locomotion such as balance and ground contact, generalizes naturally to variations in style due to changes in speed, step-length, and mass, and avoids common problems such as footskate that arise with existing trackers. The model dynamics comprises a two degree-of-freedom representation of human locomotion with inelastic ground contact. A stochastic controller generates impulsive forces during the toe-off stage of walking and spring-like forces between the legs. A higher-dimensional kinematic observation model is then conditioned on the underlying dynamics. We use the model for tracking walking people from video, including examples with turning, occlusion, and varying gait.

We introduce models for density estimation with multiple, hidden, continuous factors. In particular, we propose a generalization of multilinear models using nonlinear basis functions. By marginalizing over the weights, we obtain a multifactor form of the Gaussian process latent variable model. In this model, each factor is kernelized independently, allowing nonlinear mappings from any particular factor to the data. We learn models for human locomotion data, in which each pose is generated by factors representing the person's identity, gait, and the current state of motion. We demonstrate our approach using time-series prediction, and by synthesizing novel animation from the model.

Creating high-quality label layouts in a particular visual style is a time-consuming process. Although automated labeling algorithms can aid the layout process, expert design knowledge is required to tune these algorithms so that they produce layouts which meet the designer's expectations. We propose a system which can learn a labellayout style from a single example layout and then apply this style to new labeling problems. Because designers find it much easier to create example layouts than tune algorithmic parameters, our system provides a more natural workflow for graphic designers. We demonstrate that our system is capable of learning a variety of label layout styles from examples.

This paper describes an approach to building real-time highly-controllable characters. A kinematic character controller is built on-the-fly during a capture session, and updated after each new motion clip is acquired. Active learning is used to identify which motion sequence the user should perform next, in order to improve the quality and responsiveness of the controller. Because motion clips are selected adaptively, we avoid the difficulty of manually determining which ones to capture, and can build complex controllers from scratch while significantly reducing the number of necessary motion samples.

Camera shake during exposure leads to objectionable image blur and ruins many photographs. Conventional blind deconvolution methods typically assume frequency-domain constraints on images, or overly simplified parametric forms for the motion path during camera shake. Real camera motions can follow convoluted paths, and a spatial domain prior can better maintain visually salient image characteristics. We introduce a method to remove the effects of camera shake from seriously blurred images. The method assumes a uniform camera blur over the image and negligible in-plane camera rotation. In order to estimate the blur from the camera shake, the user must specify an image region without saturation effects. We show results for a variety of digital photographs taken from personal photo collections.

We present a purely time domain approach to speech processing which identifies waveform samples at the boundaries between glottal pulse periods (in voiced speech) or at the boundaries of unvoiced segments. An efficient algorithm for inferring these boundaries and estimating the average spectra of voiced and unvoiced regions is derived from a simple probabilistic generative model. Competitive results are presented on pitch tracking, voiced/unvoiced detection and timescale modification; all these tasks and several others can be performed using the single segmentation provided by inference in the model.

This paper describes a photometric stereo method designed for surfaces with spatially-varying BRDFs, including surfaces with both varying diffuse and specular properties. Our method builds on the observation that most objects are composed of a small number of fundamental materials. This approach recovers not only the shape but also material BRDFs and weight maps, yielding compelling results for a wide variety of objects. We also show examples of interactive lighting and editing operations made possible by our method.

We advocate the use of scaled Gaussian process latent variable models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a low-dimensional embedding of the high-dimensional pose data and a density function that both gives higher probability to points close to training data and provides a nonlinear probabilistic mapping from the low-dimensional latent space to the full-dimensional pose space. The SGPLVM is a natural choice when only small amounts of training data are available. We demonstrate our approach with two distinct motions, golfing and walking. We show that the SGPLVM sufficiently constrains the problem such that tracking can be accomplished with straightforward deterministic optimization.

We propose an algorithm that uses Gaussian process regression to learn common hidden structure shared between corresponding sets of heterogenous observations. The observation spaces are linked via a single, reduced-dimensionality latent variable space. We present results from two datasets demonstrating the algorithms's ability to synthesize novel data from learned correspondences. We first show that the method can learn the nonlinear mapping between corresponding views of objects, filling in missing data as needed to synthesize novel views. We then show that the method can learn a mapping between human degrees of freedom and robotic degrees of freedom for a humanoid robot, allowing robotic imitation of human poses from motion capture data.

This paper introduces Gaussian Process Dynamical Models (GPDM) for nonlinear time series analysis. A GPDM comprises a low-dimensional latent space with associated dynamics, and a map from the latent space to an observation space. We marginalize out the model parameters in closed-form, using Gaussian Process (GP) priors for both the dynamics and the observation mappings. This results in a nonparametric model for dynamical systems that accounts for uncertainty in the model. We demonstrate the approach on human motion capture data in which each pose is 62-dimensional. Despite the use of small data sets, the GPDM learns an effective representation of the nonlinear dynamics in these spaces. Webpage: http://www.dgp.toronto.edu/

This paper presents a technique for computing the geometry of objects with general reflectance properties from images. For surfaces with varying material properties, a full segmentation into different material types is also computed. It is assumed that the camera viewpoint is fixed, but the illumination varies over the input sequence. It is also assumed that one or more example objects with similar materials and known geometry are imaged under the same illumination conditions. Unlike most previous work in shape reconstruction, this technique can handle objects with arbitrary and spatially-varying BRDFs. Furthermore, the approach works for arbitrary distant and unknown lighting environments. Finally, almost no calibration is needed, making the approach exceptionally simple to apply.

This paper presents a novel physics-based representation of realistic character motion. The dynamical model incorporates several factors of locomotion derived from the biomechanical literature, including relative preferences for using some muscles more than others. elastic mechanisms at joints due to the mechanical properties of tendons, ligaments, and muscles, and variable stiffness at joints depending on the task. When used in a spacetime optimization framework, the parameters of this model define a wide range of styles of natural human movement.Due to the complexity of biological motion, these style parameters are too difficult to design by hand. To address this, we introduce Nonlinear Inverse Optimization, a novel algorithm for estimating optimization parameters from motion capture data. Our method can extract the physical parameters from a single short motion sequence. Once captured, this representation of style is extremely flexible: motions can be generated in the same style but performing different tasks, and styles may be edited to change the physical properties of the body.

We describe a new approach to rotoscoping --- the process of tracking contours in a video sequence --- that combines computer vision with user interaction. In order to track contours in video, the user specifies curves in two or more frames; these curves are used as keyframes by a computer-vision-based tracking algorithm. The user may interactively refine the curves and then restart the tracking algorithm. Combining computer vision with user interaction allows our system to track any sequence with significantly less effort than interpolation-based systems --- and with better reliability than "pure" computer vision systems. Our tracking algorithm is cast as a spacetime optimization problem that solves for time-varying curve shapes based on an input video sequence and user-specified constraints. We demonstrate our system with several rotoscoped examples. Additionally, we show how these rotoscoped contours can be used to help create cartoon animation by attaching user-drawn strokes to the tracked contours.

This paper presents an inverse kinematics system based on a learned model of human poses. Given a set of constraints, our system can produce the most likely pose satisfying those constraints, in real-time. Training the model on different input data leads to different styles of IK. The model is represented as a probability distribution over the space of all possible poses. This means that our IK system can generate any pose, but prefers poses that are most similar to the space of poses in the training data. We represent the probability with a novel model called a Scaled Gaussian Process Latent Variable Model. The parameters of the model are all learned automatically; no manual tuning is required for the learning component of the system. We additionally describe a novel procedure for interpolating between styles.Our style-based IK can replace conventional IK, wherever it is used in computer animation and computer vision. We demonstrate our system in the context of a number of applications: interactive character posing, trajectory keyframing, real-time motion capture with missing markers, and posing from a 2D image.

This paper presents a technique for computing the geometry of objects with general reflectance properties from images. For surfaces with varying material properties, a full segmentation into different material types is also computed. It is assumed that the camera viewpoint is fixed, but the illumination varies over the input sequence. It is also assumed that one or more example objects with similar materials and known geometry are imaged under the same illumination conditions. Unlike most previous work in shape reconstruction, this technique can handle objects with arbitrary and spatially-varying BRDFs. Furthermore, the approach works for arbitrary distant and unknown lighting environments. Finally, almost no calibration is needed, making the approach exceptionally simple to apply.

We present an algorithm for computing optical flow, shape, motion, lighting, and albedo from an image sequence of a rigidly-moving Lambertian object under distant illumination. The problem is formulated in a manner that subsumes structure from motion, multiview stereo, and photometric stereo as special cases. The algorithm utilizes both spatial and temporal intensity variation as cues: the former constrains flow and the latter constrains surface orientation; combining both cues enables dense reconstruction of both textured and textureless surfaces. The algorithm works by iteratively estimating affine camera parameters, illumination, shape, and albedo in an alternating fashion. Results are demonstrated on videos of hand-held objects moving in front of a fixed light and camera.

This paper presents an algorithm for learning the time-varying shape of a non-rigid 3D object from uncalibrated 2D tracking data. We model shape motion as a rigid component (rotation and translation) combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deforma- tions are allowed. We constrain the problem by assuming that the object shape at each time instant is drawn from a Gaussian distribution. Based on this assumption, the algorithm simultaneously estimates 3D shape and motion for each time frame, learns the parameters of the Gaussian, and robustly fills-in missing data points. We then extend the algorithm to model temporal smoothness in object shape, thus allowing it to handle severe cases of missing data.

It is argued that computer graphics can benefit from a deeper use of machine learning techniques. The author gives an overview of what learning has to offer the graphics community, with an emphasis on Bayesian techniques. He also attempts to address some misconceptions about learning, and to give a very brief tutorial on Bayesian reasoning.

We use relaxation to produce painted imagery from images and video. An energy function is first specified; we then search for a painting with minimal energy. The appeal of this strategy is that, ideally, we need only specify what we want, not how to directly compute it. Because the energy function is very difficult to optimize, we use a relaxation algorithm combined with search heuristics. This formulation allows us to specify painting style by varying the relative weights of energy terms. The basic energy function yields an economical style that conveys an image with few strokes. This style produces greater temporal coherence for video than previous techniques. The system allows as fine user control as desired: the user may interactively change the painting style, specify variations of style over an image, and/or add specific strokes to the painting.

This paper describes a new framework for processing images by example, called “image analogies.” The framework involves two stages: a design phase, in which a pair of images, with one image purported to be a “filtered” version of the other, is presented as “training data”; and an application phase, in which the learned filter is applied to some new target image in order to create an “analogous” filtered result. Image analogies are based on a simple multi-scale autoregression, inspired primarily by recent results in texture synthesis. By choosing different types of source image pairs as input, the framework supports a wide variety of “image filter” effects, including traditional image filters, such as blurring or embossing; improved texture synthesis, in which some textures are synthesized with higher quality than by previous approaches; super-resolution, in which a higher-resolution image is inferred from a low-resolution source; texture transfer, in which images are “texturized” with some arbitrary source texture; artistic filters, in which various drawing and painting styles are synthesized based on scanned real-world examples; and texture-by-numbers, in which realistic scenes, composed of a variety of textures, are created using a simple painting interface.

The paper addresses the problem of recovering 3D non-rigid shape models from image sequences. For example, given a video recording of a talking person, we would like to estimate a 3D model of the lips and the full face and its internal modes of variation. Many solutions that recover 3D shape from 2D image sequences have been proposed; these so-called structure-from-motion techniques usually assume that the 3D object is rigid. For example, C. Tomasi and T. Kanades' (1992) factorization technique is based on a rigid shape matrix, which produces a tracking matrix of rank 3 under orthographic projection. We propose a novel technique based on a non-rigid model, where the 3D shape in each frame is a linear combination of a set of basis shapes. Under this model, the tracking matrix is of higher rank, and can be factored in a three-step process to yield pose, configuration and shape. To the best of our knowledge, this is the first model free approach that can recover from single-view video sequences nonrigid shape models. We demonstrate this new algorithm on several video sequences. We were able to recover 3D non-rigid human face and animal models with high accuracy.

We approach the problem of stylistic motion synthesis by learning motion patterns from a highly varied set of motion capture sequences. Each sequence may have a distinct choreography, performed in a distinct sytle. Learning identifies common choreographic elements across sequences, the different styles in which each element is performed, and a small number of stylistic degrees of freedom which span the many variations in the dataset. The learned model can synthesize novel motion data in any interpolation or extrapolation of styles. For example, it can convert novice ballet motions into the more graceful modern dance of an expert. The model can also be driven by video, by scripts or even by noise to generate new choreography and synthesize virtual motion-capture in many styles.

We present a new set of algorithms for line-art rendering of smooth surfaces. We introduce an efficient, deterministic algorithm for finding silhouettes based on geometric duality, and an algorithm for segmenting the silhouette curves into smooth parts with constant visibility. These methods can be used to find all silhouettes in real time in software. We present an automatic method for generating hatch marks in order to convey surface shape. We demonstrate these algorithms with a drawing style inspired by A Topological Picturebook by G. Francis.

We present a new method for creating an image with a handpainted appearance from a photograph, and a new approach to designing styles of illustration. We "paint" an image with a series of spline brush strokes. Brush strokes are chosen to match colors in a source image. A painting is built up in a series of layers, starting with a rough sketch drawn with a large brush. The sketch is painted over with progressively smaller brushes, but only in areas where the sketch differs from the blurred source image. Thus, visual emphasis in the painting corresponds roughly to the spatial energy present in the source image. We demonstrate a technique for painting with long, curved brush strokes, aligned to normals of image gradients. Thus we begin to explore the expressive quality of complex brush strokes. Rather than process images with a single manner of painting, we present a framework for describing a wide range of visual styles. A style is described as an intuitive set of parameters to the pain...