Search

The Laplace Beltrami operator is one of the essential tools in geometric processing. It allows us to solve numerous partial differential equations on discrete surface meshes, which is a fundamental building block in many computer graphics applications. Discrete Laplacians are typically limited to standard elements like triangles or quadrilaterals, which severely constrains the tessellation of the mesh. But in recent years, several approaches were able to generalize the Laplace Beltrami and its closely related gradient and divergence operators to more general meshes. This allows artists and engineers to work with a wider range of elements which are sometimes required and beneficial in their field. This paper discusses the different constructions of these three ubiquitous differential operators on arbitrary polygons and analyzes their individual advantages and properties in common computer graphics applications. [ABSTRACT FROM AUTHOR]

Parametric 3D shape models are heavily utilized in computer graphics and vision applications to provide priors on the observed variability of an object's geometry (e.g., for faces). Original models were linear and operated on the entire shape at once. They were later enhanced to provide localized control on different shape parts separately. In deep shape models, nonlinearity was introduced via a sequence of fully‐connected layers and activation functions, and locality was introduced in recent models that use mesh convolution networks. As common limitations, these models often dictate, in one way or another, the allowed extent of spatial correlations and also require that a fixed mesh topology be specified ahead of time. To overcome these limitations, we present Shape Transformers, a new nonlinear parametric 3D shape model based on transformer architectures. A key benefit of this new model comes from using the transformer's self‐attention mechanism to automatically learn nonlinear spatial correlations for a class of 3D shapes. This is in contrast to global models that correlate everything and local models that dictate the correlation extent. Our transformer 3D shape autoencoder is a better alternative to mesh convolution models, which require specially‐crafted convolution, and down/up‐sampling operators that can be difficult to design. Our model is also topologically independent: it can be trained once and then evaluated on any mesh topology, unlike most previous methods. We demonstrate the application of our model to different datasets, including 3D faces, 3D hand shapes and full human bodies. Our experiments demonstrate the strong potential of our Shape Transformer model in several applications in computer graphics and vision. [ABSTRACT FROM AUTHOR]

Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed‐form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end‐to‐end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approach insensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise in this context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the label decision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint predictions for models from different object categories and for different viewpoint qualities. Additionally, we show that prediction times are reduced from several minutes to a fraction of a second, as compared to state‐of‐the‐art (SOTA) viewpoint quality evaluation. Code and training data is available at https://github.com/schellmi42/viewpoint%5flearning, which is to our knowledge the biggest viewpoint quality dataset available. [ABSTRACT FROM AUTHOR]

Image synthesis designed for machine learning applications provides the means to efficiently generate large quantities of training data while controlling the generation process to provide the best distribution and content variety. With the demands of deep learning applications, synthetic data have the potential of becoming a vital component in the training pipeline. Over the last decade, a wide variety of training data generation methods has been demonstrated. The potential of future development calls to bring these together for comparison and categorization. This survey provides a comprehensive list of the existing image synthesis methods for visual machine learning. These are categorized in the context of image generation, using a taxonomy based on modelling and rendering, while a classification is also made concerning the computer vision applications they are used. We focus on the computer graphics aspects of the methods, to promote future image generation for machine learning. Finally, each method is assessed in terms of quality and reported performance, providing a hint on its expected learning potential. The report serves as a comprehensive reference, targeting both groups of the applications and data development sides. A list of all methods and papers reviewed herein can be found at https://computergraphics.on.liu.se/image_synthesis_methods_for_visual_machine_learning/. [ABSTRACT FROM AUTHOR]

We present a practical method to synthesize plausible 3D facial expressions for a particular target subject. The ability to synthesize an entire facial rig from a single neutral expression has a large range of applications both in computer graphics and computer vision, ranging from the efficient and cost‐effective creation of CG characters to scalable data generation for machine learning purposes. Unlike previous methods based on multilinear models, the proposed approach is capable to extrapolate well outside the sample pool, which allows it to plausibly predict the identity of the target subject and create artifact free expression shapes while requiring only a small input dataset. We introduce global‐local multilinear models that leverage the strengths of expression‐specific and identity‐specific local models combined with coarse motion estimations from a global model. Experimental results show that we achieve high‐quality, plausible facial expression synthesis results for an individual that outperform existing methods both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Light field (LF) reconstruction is a fundamental technique in light field imaging and has applications in both software and hardware aspects. This paper presents an unsupervised learning method for LF‐oriented view synthesis, which provides a simple solution for generating quality light fields from a sparse set of views. The method is built on disparity estimation and image warping. Specifically, we first use per‐view disparity as a geometry proxy to warp input views to novel views. Then we compensate the occlusion with a network by a forward‐backward warping process. Cycle‐consistency between different views are explored to enable unsupervised learning and accurate synthesis. The method overcomes the drawbacks of fully supervised learning methods that require large labeled training dataset and epipolar plane image based interpolation methods that do not make full use of geometry consistency in LFs. Experimental results demonstrate that the proposed method can generate high quality views for LF, which outperforms unsupervised approaches and is comparable to fully‐supervised approaches. [ABSTRACT FROM AUTHOR]

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 FROM AUTHOR]

In this report, we review the current state of the art of web-based visualization applications. Recently, an increasing number of web-based visualization applications have emerged. This is due to the fact that new technologies offered by modern browsers greatly increased the capabilities for visualizations on the web. We first review these technical aspects that are enabling this development. This includes not only improvements for local rendering like WebGL and HTML5, but also infrastructures like grid or cloud computing platforms. Another important factor is the transfer of data between the server and the client. Therefore, we also discuss advances in this field, for example methods to reduce bandwidth requirements like compression and other optimizations such as progressive rendering and streaming. After establishing these technical foundations, we review existing web-based visualization applications and prototypes from various application domains. Furthermore, we propose a classification of these web-based applications based on the technologies and algorithms they employ. Finally, we also discuss promising application areas that would benefit from web-based visualization and assess their feasibility based on the existing approaches. [ABSTRACT FROM AUTHOR]

The comparison of molecular surface attributes is of interest for computer aided drug design and the analysis of biochemical simulations. Due to the non-rigid nature of molecular surfaces, partial shape matching is feasible for mapping two surfaces onto each other. We present a novel technique to obtain a mapping relation between two surfaces using a deformable model approach. This relation is used for pair-wise comparison of local surface attributes (e.g. electrostatic potential). We combine the difference value as well as the comparability as derived from the local matching quality in a 3D molecular visualization by mapping them to color. A 2D matrix shows the global dissimilarity in an overview of different data sets in an ensemble. We apply our visualizations to simulation results provided by collaborators from the field of biochemistry to evaluate the effectiveness of our results. [ABSTRACT FROM AUTHOR]

The ability to accurately achieve performance capture of athlete motion during competitive play in near real-time promises to revolutionize not only broadcast sports graphics visualization and commentary, but also potentially performance analysis, sports medicine, fantasy sports and wagering. In this paper, we present a highly portable, non-intrusive approach for synthesizing human athlete motion in competitive game-play with lightweight instrumentation of both the athlete and field of play. Our data-driven puppetry technique relies on a pre-captured database of short segments of motion capture data to construct a motion graph augmented with interpolated motions and speed variations. An athlete's performed motion is synthesized by finding a related action sequence through the motion graph using a sparse set of measurements from the performance, acquired from both worn inertial and global location sensors. We demonstrate the efficacy of our approach in a challenging application scenario, with a high-performance tennis athlete wearing one or more lightweight body-worn accelerometers and a single overhead camera providing the athlete's global position and orientation data. However, the approach is flexible in both the number and variety of input sensor data used. The technique can also be adopted for searching a motion graph efficiently in linear time in alternative applications. [ABSTRACT FROM AUTHOR]

Creating realistic human movement is a time consuming and labour intensive task. The major difficulty is that the user has to edit individual joints while maintaining an overall realistic and collision free posture. Previous research suggests the use of data-driven inverse kinematics, such that one can focus on the control of a few joints, while the system automatically composes a natural posture. However, as a common problem of kinematics synthesis, penetration of body parts is difficult to avoid in complex movements. In this paper, we propose a new data-driven inverse kinematics framework that conserves the topology of the synthesizing postures. Our system monitors and regulates the topology changes using the Gauss Linking Integral (GUI), such that penetration can be efficiently prevented. As a result, complex motions with tight body movements, as well as those involving interaction with external objects, can be simulated with minimal manual intervention. Experimental results show that using our system, the user can create high quality human motion in real-time by controlling a few joints using a mouse or a multi-touch screen. The movement generated is both realistic and penetration free. Our system is best applied for interactive motion design in computer animations and games. [ABSTRACT FROM AUTHOR]

The computation of intrinsic, geodesic distances and geodesic paths on surfaces is a fundamental low-level building block in countless Computer Graphics and Geometry Processing applications. This demand led to the development of numerous algorithms - some for the exact, others for the approximative computation, some focussing on speed, others providing strict guarantees. Most of these methods are designed for computing distances according to the standard Riemannian metric induced by the surface's embedding in Euclidean space. Generalization to other, especially anisotropic, metrics - which more recently gained interest in several application areas - is not rarely hampered by fundamental problems. We explore and discuss possibilities for the generalization and extension of well-known methods to the anisotropic case, evaluate their relative performance in terms of accuracy and speed, and propose a novel algorithm, the Short-Term Vector Dijkstra. This algorithm is strikingly simple to implement and proves to provide practical accuracy at a higher speed than generalized previous methods. [ABSTRACT FROM AUTHOR]

Rigid registration of two geometric data sets is essential in many applications, including robot navigation, surface reconstruction, and shape matching. Most commonly, variants of the Iterative Closest Point (ICP) algorithm are employed for this task. These methods alternate between closest point computations to establish correspondences between two data sets, and solving for the optimal transformation that brings these correspondences into alignment. A major difficulty for this approach is the sensitivity to outliers and missing data often observed in 3D scans. Most practical implementations of the ICP algorithm address this issue with a number of heuristics to prune or reweight correspondences. However, these heuristics can be unreliable and difficult to tune, which often requires substantial manual assistance. We propose a new formulation of the ICP algorithm that avoids these difficulties by formulating the registration optimization using sparsity inducing norms. Our new algorithm retains the simple structure of the ICP algorithm, while achieving superior registration results when dealing with outliers and incomplete data. The complete source code of our implementation is provided at http://lgg.epfl.ch/sparseicp. [ABSTRACT FROM AUTHOR]

This paper presents a novel example-based stippling technique that employs a simple and intuitive concept to convert a color image into a pointillism painting. Our method relies on analyzing and imitating the color distributions of Seurat's paintings to obtain a statistical color model. Then, this model can be easily combined with the modified multi-class blue noise sampling to stylize an input image with characteristics of color composition in Seurat's paintings. The blue noise property of the output image also ensures that the color points are randomly located but remain spatially uniform. In our experiments, the multivariate goodness-of-fit tests were adopted to quantitatively analyze the results of the proposed and previous methods, further confirming that the color composition of our results are more similar to Seurat's painting style than that of previous approaches. Additionally, we also conducted a user study participated by artists to qualitatively evaluate the synthesized images of the proposed method. [ABSTRACT FROM AUTHOR]

Massive amount of movement data, such as daily trips made by millions of passengers in a city, are widely available nowadays. They are a highly valuable means not only for unveiling human mobility patterns, but also for assisting transportation planning, in particular for metropolises around the world. In this paper, we focus on a novel aspect of visualizing and analyzing massive movement data, i.e., the interchange pattern, aiming at revealing passenger redistribution in a traffic network. We first formulate a new model of circos figure, namely the interchange circos diagram, to present interchange patterns at a junction node in a bundled fashion, and optimize the color assignments to respect the connections within and between junction nodes. Based on this, we develop a family of visual analysis techniques to help users interactively study interchange patterns in a spatiotemporal manner: 1) multi-spatial scales: from network junctions such as train stations to people flow across and between larger spatial areas; and 2) temporal changes of patterns from different times of the day. Our techniques have been applied to real movement data consisting of hundred thousands of trips, and we present also two case studies on how transportation experts worked with our interface. [ABSTRACT FROM AUTHOR]

We introduce the Sifted Disk technique for locally resampling a point cloud in order to reduce the number of points. Two neighboring points are removed and we attempt to find a single random point that is sufficient to replace them both. The resampling respects the original sizing function; In that sense it is not a coarsening. The angle and edge length guarantees of a Delaunay triangulation of the points are preserved. The sifted point cloud is still suitable for texture synthesis because the Fourier spectrum is largely unchanged. We provide an efficient algorithm, and demonstrate that sifting uniform Maximal Poisson-disk Sampling (MPS) and Delaunay Refinement (DR) points reduces the number of points by about 25%, and achieves a density about 1/3 more than the theoretical minimum. We show two-dimensional stippling and meshing applications to demonstrate the significance of the concept. [ABSTRACT FROM AUTHOR]

Ray tracing has become a viable alternative to rasterization for interactive applications and also forms the basis of most global illumination methods. However, even today's fastest ray-tracers offer only a tight budget of rays per pixel per frame. Rendering performance can be improved by increasing this budget, or by developing methods that use it more efficiently. In this paper we propose a global visibility caching algorithm that reduces the number of shadow rays required for shading to a fraction of less than 2% in some cases. We quantize the visibility function's domain while ensuring a minimal degradation of the final image quality. To control the introduced error, we adapt the quantization locally, accounting for variations in geometry, sampling densities on both endpoints of the visibility queries, and the light signal itself. Compared to previous approaches for approximating visibility, e.g. shadow mapping, our method has several advantages: (1) it allows caching of arbitrary visibility queries between surface points and is thus applicable to all ray tracing based methods; (2) the approximation error is uniform over the entire image and can be bounded by a user-specified parameter; (3) the cache is created on-the-fly and does not waste any resources on queries that will never be used. We demonstrate the benefits of our method on Whitted-style ray tracing combined with instant radiosity, as well as an integration with bidirectional path tracing. [ABSTRACT FROM AUTHOR]

The use of Laplacian eigenbases has been shown to be fruitful in many computer graphics applications. Today, state-of-the-art approaches to shape analysis, synthesis, and correspondence rely on these natural harmonic bases that allow using classical tools from harmonic analysis on manifolds. However, many applications involving multiple shapes are obstacled by the fact that Laplacian eigenbases computed independently on different shapes are often incompatible with each other. In this paper, we propose the construction of common approximate eigenbases for multiple shapes using approximate joint diagonalization algorithms, taking as input a set of corresponding functions (e.g. indicator functions of stable regions) on the two shapes. We illustrate the benefits of the proposed approach on tasks from shape editing, pose transfer, correspondence, and similarity. [ABSTRACT FROM AUTHOR]

Urban facades regularly contain interesting variations due to allowed deformations of repeated elements (e.g., windows in different open or close positions) posing challenges to state-of-the-art facade analysis algorithms. We propose a semi-automatic framework to recover both repetition patterns of the elements and their individual deformation parameters to produce a factored facade representation. Such a representation enables a range of applications including interactive facade images, improved multi-view stereo reconstruction, facade-level change detection, and novel image editing possibilities. [ABSTRACT FROM AUTHOR]

Super-deformed, SD, is a specific artistic style for Japanese manga and anime which exaggerates characters in the goal of appearing cute and funny. The SD style characters are widely used, and can be seen in many anime, CG movies, or games. However, to create an SD model often requires professional skills and considerable time and effort. In this paper, we present a novel technique to generate an SD style counterpart of a normal 3D character model. Our approach uses an optimization guided by a number of constraints that can capture the properties of the SD style. Users can also customize the results by specifying a small set of parameters related to the body proportions and the emphasis of the signature characteristics. With our technique, even a novel user can generate visually pleasing SD models in seconds. [ABSTRACT FROM AUTHOR]

We provide two contributions, a taxonomy of visual cluster separation factors in scatterplots, and an in-depth qualitative evaluation of two recently proposed and validated separation measures. We initially intended to use these measures to provide guidance for the use of dimension reduction (DR) techniques and visual encoding (VE) choices, but found that they failed to produce reliable results. To understand why, we conducted a systematic qualitative data study covering a broad collection of 75 real and synthetic high-dimensional datasets, four DR techniques, and three scatterplot-based visual encodings. Two authors visually inspected over 800 plots to determine whether or not the measures created plausible results. We found that they failed in over half the cases overall, and in over two-thirds of the cases involving real datasets. Using open and axial coding of failure reasons and separability characteristics, we generated a taxonomy of visual cluster separability factors. We iteratively refined its explanatory clarity and power by mapping the studied datasets and success and failure ranges of the measures onto the factor axes. Our taxonomy has four categories, ordered by their ability to influence successors: Scale, Point Distance, Shape, and Position. Each category is split into Within-Cluster factors such as density, curvature, isotropy, and clumpiness, and Between-Cluster factors that arise from the variance of these properties, culminating in the overarching factor of class separation. The resulting taxonomy can be used to guide the design and the evaluation of cluster separation measures. [ABSTRACT FROM AUTHOR]

This paper introduces a method for automatically generating continuous line illustrations, drawings consisting of a single line, from a given input image. Our approach begins by inferring a graph from a set of edges extracted from the image in question and obtaining a path that traverses through all edges of the said graph. The resulting path is then subjected to a series of post-processing operations to transform it into a continuous line drawing. Moreover, our approach allows us to manipulate the amount of detail portrayed in our line illustrations, which is particularly useful for simplifying the overall illustration while still retaining its most significant features. We also present several experimental results to demonstrate that our approach can automatically synthesize continuous line illustrations comparable to those of some contemporary artists. [ABSTRACT FROM AUTHOR]

Interactive information visualization systems rely on widgets to allow users to interact with the data and modify the representation. We define interactive legends as a class of controls combining the visual representation of static legends and interaction mechanisms of widgets. As interactive legends start to appear in popular websites, we categorize their designs for common data types and evaluate their effectiveness compare to standard widgets. Results suggest that 1) interactive legends can lead to faster perception of the mapping between data values and visual encodings and 2) interaction time is affected differently depending on the data type. Additionally, our study indicates superiority both in terms of perception and interaction of ordinal controls over numerical ones. Numerical techniques are mostly used in today's systems. By providing solutions to allowing users to modify ranges interactively, we believe that interactive legends make it possible to increase the use of ordinal techniques for visual exploration. [ABSTRACT FROM AUTHOR]

We present an interface for 3D object manipulation in which standard transformation tools are replaced with transient 3D widgets invoked by sketching context-dependent strokes. The widgets are automatically aligned to axes and planes determined by the user's stroke. Sketched pivot-points further expand the interaction vocabulary. Using gestural commands, these basic elements can be assembled into dynamic, user-constructed 3D transformation systems. We supplement precise widget interaction with techniques for coarse object positioning and snapping. Our approach, which is implemented within a broader sketch-based modeling system, also integrates an underlying “widget history” to enable the fluid transfer of widgets between objects. An evaluation indicates that users familiar with 3D manipulation concepts can be taught how to efficiently use our system in under an hour. [ABSTRACT FROM AUTHOR]

The rapid increase in the performance of graphics hardware, coupled with recent improvements in its programmability, have made graphics hardware a compelling platform for computationally demanding tasks in a wide variety of application domains. In this report, we describe, summarize, and analyze the latest research in mapping general-purpose computation to graphics hardware. We begin with the technical motivations that underlie general-purpose computation on graphics processors (GPGPU) and describe the hardware and software developments that have led to the recent interest in this field. We then aim the main body of this report at two separate audiences. First, we describe the techniques used in mapping general-purpose computation to graphics hardware. We believe these techniques will be generally useful for researchers who plan to develop the next generation of GPGPU algorithms and techniques. Second, we survey and categorize the latest developments in general-purpose application development on graphics hardware. [ABSTRACT FROM AUTHOR]