EG2016
Permanent URI for this community
Browse
Browsing EG2016 by Issue Date
Now showing 1 - 20 of 116
Results Per Page
Sort Options
Item Automatic Portrait Segmentation for Image Stylization(The Eurographics Association and John Wiley & Sons Ltd., 2016) Shen, Xiaoyong; Hertzmann, Aaron; Jia, Jiaya; Paris, Sylvain; Price, Brian; Shechtman, Eli; Sachs, Ian; Joaquim Jorge and Ming LinPortraiture 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.Item Geometry and Attribute Compression for Voxel Scenes(The Eurographics Association and John Wiley & Sons Ltd., 2016) Dado, Bas; Kol, Timothy R.; Bauszat, Pablo; Thiery, Jean-Marc; Eisemann, Elmar; Joaquim Jorge and Ming LinVoxel-based approaches are today's standard to encode volume data. Recently, directed acyclic graphs (DAGs) were successfully used for compressing sparse voxel scenes as well, but they are restricted to a single bit of (geometry) information per voxel. We present a method to compress arbitrary data, such as colors, normals, or reflectance information. By decoupling geometry and voxel data via a novel mapping scheme, we are able to apply the DAG principle to encode the topology, while using a palette-based compression for the voxel attributes, leading to a drastic memory reduction. Our method outperforms existing state-of-the-art techniques and is well-suited for GPU architectures. We achieve real-time performance on commodity hardware for colored scenes with up to 17 hierarchical levels (a 128K3 voxel resolution), which are stored fully in core.Item Directional Field Synthesis, Design, and Processing(The Eurographics Association and John Wiley & Sons Ltd., 2016) Vaxman, Amir; Campen, Marcel; Diamanti, Olga; Panozzo, Daniele; Bommes, David; Hildebrandt, Klaus; Ben-Chen, Mirela; Joaquim Madeira and Gustavo PatowDirection fields and vector fields play an increasingly important role in computer graphics and geometry processing. The synthesis of directional fields on surfaces, or other spatial domains, is a fundamental step in numerous applications, such as mesh generation, deformation, texture mapping, and many more. The wide range of applications resulted in definitions for many types of directional fields: from vector and tensor fields, over line and cross fields, to frame and vector-set fields. Depending on the application at hand, researchers have used various notions of objectives and constraints to synthesize such fields. These notions are defined in terms of fairness, feature alignment, symmetry, or field topology, to mention just a few. To facilitate these objectives, various representations, discretizations, and optimization strategies have been developed. These choices come with varying strengths and weaknesses. This report provides a systematic overview of directional field synthesis for graphics applications, the challenges it poses, and the methods developed in recent years to address these challenges.Item A Simple and Effective Method to Detect Orthogonal Vanishing Points in Uncalibrated Images of Man-Made Environments(The Eurographics Association, 2016) Simon, Gilles; Fond, Antoine; Berger, Marie-Odile; T. Bashford-Rogers and L. P. SantosThis paper presents an effective and easy-to-implement algorithm to compute orthogonal vanishing points in uncalibrated images of man-made scenes. The main contribution is to estimate the zenith and the horizon line before detecting the vanishing points, using simple properties of the central projection and exploiting accumulations of oriented segments around the horizon. Our method is fast and yields an accuracy comparable, and even better in some cases, to that of state-of-the-art algorithms.Item EUROGRAPHICS 2016: Tutorials Frontmatter(Eurographics Association, 2016) Sousa, A. Augusto; Bouatouch, Kadi;Item The HDR-video Pipeline(The Eurographics Association, 2016) Unger, Jonas; Banterle, Francesco; Eilertsen, Gabriel; Mantiuk, Rafał K.; Augusto Sousa and Kadi BouatouchHigh dynamic range (HDR) video technology has gone through remarkable developments over the last few years; HDR-video cameras are being commercialized, new algorithms for color grading and tone mapping specifically designed for HDR-video have recently been proposed, and the first open source compression algorithms for HDR- video are becoming available. HDR-video represents a paradigm shift in imaging and computer graphics, which has and will continue to generate a range of both new research challenges and applications. This intermediate- level tutorial will give an in-depth overview of the full HDR-video pipeline present several examples of state-of- the-art algorithms and technology in HDR-video capture, tone mapping, compression and specific applications in computer graphics.Item Compressed Multiresolution Hierarchies for High-Quality Precomputed Shadows(The Eurographics Association and John Wiley & Sons Ltd., 2016) Scandolo, Leonardo; Bauszat, Pablo; Eisemann, Elmar; Joaquim Jorge and Ming LinThe quality of shadow mapping is traditionally limited by texture resolution. We present a novel lossless compression scheme for high-resolution shadow maps based on precomputed multiresolution hierarchies. Traditional multiresolution trees can compactly represent homogeneous regions of shadow maps at coarser levels, but require many nodes for fine details. By conservatively adapting the depth map, we can significantly reduce the tree complexity. Our proposed method offers high compression rates, avoids quantization errors, exploits coherency along all data dimensions, and is well-suited for GPU architectures. Our approach can be applied for coherent shadow maps as well, enabling several applications, including high-quality soft shadows and dynamic lights moving on fixed-trajectories.Item 3D Characters for Virtual Reality(The Eurographics Association, 2016) Orvalho, Veronica; Runa, Catarina; Lewis, John P.; Augusto Sousa and Kadi BouatouchCreating a 3D avatar that looks like a specific person is timeconsuming, requires expert artists, expensive equipment and a complex pipeline. In this tutorial we explain the different stages of a traditional character animation pipeline: modeling, rigging and animation. But, most important we describe how each of this stages bind together and which are the challenges developers face today at each stage. Our ultimate goal is to explain stepbystep the creation of a unified facial animation pipeline. We build the tutorial over our experience on what worked, what didn't work, why we did what we did and how we are planning to improve in the future. Given the popularity of Virtual Reality since the launching of Oculus Rift, we also describe how a traditional animation pipeline can be applied in Virtual Reality, it's challenges, limitations and potential. Throughout the tutorial we introduce the theoretical background for character animation and present the current state of the art in this field. Last, we aim to trigger a discussion to analyse different lines of research that emerge by bringing together traditional character animation and Virtual Reality.Item Peripheral Retinal Image Simulation Based on Retina Shapes(The Eurographics Association, 2016) Dias, Catarina; Wick, Michael; Rifai, Katharina; Wahl, Siegfried; T. Bashford-Rogers and L. P. SantosWe present a method to render the image of a scene reaching the retina, the retinal image, taking into account human offaxis optical aberrations. To this end, we consider realistic wide-angle eye models that offer an anatomical description of the refractive structures of the eye as a set of lenses and accurately reproduce the optical aberrations in the periphery. We then combine these with representative retinal shapes and with distributed ray tracing. Due to the interplay between the eye model and the curved retina, we obtain a realistic simulation of the retinal image, not only foveally but also in the periphery.Item Inertial Steady 2D Vector Field Topology(The Eurographics Association and John Wiley & Sons Ltd., 2016) Günther, Tobias; Theisel, Holger; Joaquim Jorge and Ming LinVector field topology is a powerful and matured tool for the study of the asymptotic behavior of tracer particles in steady flows. Yet, it does not capture the behavior of finite-sized particles, because they develop inertia and do not move tangential to the flow. In this paper, we use the fact that the trajectories of inertial particles can be described as tangent curves of a higher dimensional vector field. Using this, we conduct a full classification of the first-order critical points of this higher dimensional flow, and devise a method to their efficient extraction. Further, we interactively visualize the asymptotic behavior of finite-sized particles by a glyph visualization that encodes the outcome of any initial condition of the governing ODE, i.e., for a varying initial position and/or initial velocity. With this, we present a first approach to extend traditional vector field topology to the inertial case.Item VBTC: GPU-Friendly Variable Block Size Texture Encoding(The Eurographics Association and John Wiley & Sons Ltd., 2016) Krajcevski, Pavel; Golas, Abhinav; Ramani, Karthik; Shebanow, Michael; Manocha, Dinesh; Joaquim Jorge and Ming LinRecent advances in computer graphics have relied on high-quality textures in order to generate photorealistic real-time images. Texture compression standards meet these growing demands for data, but current texture compression schemes use fixed-rate methods where statically sized blocks of pixels are represented using the same numbers of bits irrespective of their data content. In order to account for the natural variation in detail, we present an alternative format that allows variable bit-rate texture compression with minimal changes to texturing hardware. Our proposed scheme uses one additional level of indirection to allow the variation of the block size across the same texture. This single change is exploited to both vary the amount of bits allocated to certain parts of the texture and to duplicate redundant texture information across multiple pixels. To minimize hardware changes, the method picks combinations of block sizes and compression methods from existing fixed-rate standards. With this approach, our method is able to demonstrate energy savings of up to 50%, as well as higher quality compressed textures over current state of the art techniques.Item DeepProp: Extracting Deep Features from a Single Image for Edit Propagation(The Eurographics Association and John Wiley & Sons Ltd., 2016) Endo, Yuki; Iizuka, Satoshi; Kanamori, Yoshihiro; Mitani, Jun; Joaquim Jorge and Ming LinEdit propagation is a technique that can propagate various image edits (e.g., colorization and recoloring) performed via user strokes to the entire image based on similarity of image features. In most previous work, users must manually determine the importance of each image feature (e.g., color, coordinates, and textures) in accordance with their needs and target images. We focus on representation learning that automatically learns feature representations only from user strokes in a single image instead of tuning existing features manually. To this end, this paper proposes an edit propagation method using a deep neural network (DNN). Our DNN, which consists of several layers such as convolutional layers and a feature combiner, extracts strokeadapted visual features and spatial features, and then adjusts the importance of them. We also develop a learning algorithm for our DNN that does not suffer from the vanishing gradient problem, and hence avoids falling into undesirable locally optimal solutions. We demonstrate that edit propagation with deep features, without manual feature tuning, can achieve better results than previous work.Item Building Construction Sets by Tiling Grammar Simplification(The Eurographics Association and John Wiley & Sons Ltd., 2016) Kalojanov, Javor; Wand, Michael; Slusallek, Philipp; Joaquim Jorge and Ming LinThis paper poses the problem of fabricating physical construction sets from example geometry: A construction set provides a small number of different types of building blocks from which the example model as well as many similar variants can be reassembled. This process is formalized by tiling grammars. Our core contribution is an approach for simplifying tiling grammars such that we obtain physically manufacturable building blocks of controllable granularity while retaining variability, i.e., the ability to construct many different, related shapes. Simplification is performed by sequences of two types of elementary operations: non-local joint edge collapses in the tile graphs reduce the granularity of the decomposition and approximate replacement operations reduce redundancy. We evaluate our method on abstract graph grammars in addition to computing several physical construction sets, which are manufactured using a commodity 3D printer.Item Peer Review: Does it really help students?(The Eurographics Association, 2016) Kenwright, Ben; Beatriz Sousa Santos and Jean-Michel DischlerStudent peer review has long been a method for increasing student engagement and work quality.We present notes on teaching tips and techniques using peer review as a means way to engage students interest in the area of computer graphics and interactive animation. We address questions, such as, when feedback fails, why students should be ‘trained’ on feedback, and what constitutes a ‘constructive’ review. We present a case study around the structure and workings of a module - and its success in encouraging collaborative working, group discussions, public engagement (e.g., through wikis and events), and peer review work.Item Tonal Art Maps with Image Space Strokes(The Eurographics Association, 2016) Szécsi, László; Szirányi, Marcell; Kacsó, Ágota; Luis Gonzaga Magalhaes and Rafal MantiukThis paper presents a hybrid hatching solution that uses robust and fast texture space hatching to gather stroke fragments, but fits stylized brush strokes over those fragments in image space. Thus we obtain a real-time solution that avoids the challenges associated with hidden stroke removal in image space approaches, but allows for the artistic stylization of strokes exceeding the limitations of texture space methods. This includes strokes running over outlines or behind occluders, uniquely random strokes, and adherence to image space brush properties.Item Generalized Diffusion Curves: An Improved Vector Representation for Smooth-Shaded Images(The Eurographics Association and John Wiley & Sons Ltd., 2016) Jeschke, Stefan; Joaquim Jorge and Ming LinThis paper generalizes the well-known Diffusion Curves Images (DCI), which are composed of a set of Bezier curves with colors specified on either side. These colors are diffused as Laplace functions over the image domain, which results in smooth color gradients interrupted by the Bezier curves. Our new formulation allows for more color control away from the boundary, providing a similar expressive power as recent Bilaplace image models without introducing associated issues and computational costs. The new model is based on a special Laplace function blending and a new edge blur formulation. We demonstrate that given some user-defined boundary curves over an input raster image, fitting colors and edge blur from the image to the new model and subsequent editing and animation is equally convenient as with DCIs. Numerous examples and comparisons to DCIs are presented.Item Fast and Robust Inversion-Free Shape Manipulation(The Eurographics Association and John Wiley & Sons Ltd., 2016) Liu, Tiantian; Gao, Ming; Zhu, Lifeng; Sifakis, Eftychios; Kavan, Ladislav; Joaquim Jorge and Ming LinWe present a shape manipulation technique capable of producing deformations of 2D and 3D meshes, guaranteeing that no elements will be inverted. We achieve this by augmenting the quadratic ex-rotated elastic energy with additional convex terms that penalize the presence of inverted elements. Using a schedule of increasing penalty coefficients, we efficiently and robustly converge to an inversion free state by solving a sequence of unconstrained convex minimization problems. This process can be interpreted as a special purpose Semi-Definite Programming (SDP) solver. We demonstrate that our method outperforms solvers used in previous work, including commercial-grade SDP software (MOSEK). As an additional benefit, our method also converges to the solution via a more intuitive path, which can be used for quick preview. We demonstrate the efficacy of our scheme in a number of 2D and 3D shapes undergoing moderate to drastic deformation.Item Large Scale Terrain Generation from Tectonic Uplift and Fluvial Erosion(The Eurographics Association and John Wiley & Sons Ltd., 2016) Cordonnier, Guillaume; Braun, Jean; Cani, Marie-Paule; Benes, Bedrich; Galin, Éric; Peytavie, Adrien; Guérin, Éric; Joaquim Jorge and Ming LinAt large scale, landscapes result from the combination of two major processes: tectonics which generate the main relief through crust uplift, and weather which accounts for erosion. This paper presents the first method in computer graphics that combines uplift and hydraulic erosion to generate visually plausible terrains. Given a user-painted uplift map, we generate a stream graph over the entire domain embedding elevation information and stream flow. Our approach relies on the stream power equation introduced in geology for hydraulic erosion. By combining crust uplift and stream power erosion we generate large realistic terrains at a low computational cost. Finally, we convert this graph into a digital elevation model by blending landform feature kernels whose parameters are derived from the information in the graph. Our method gives high-level control over the large scale dendritic structures of the resulting river networks, watersheds, and mountains ridges.Item Deep Learning for Shape Analysis(The Eurographics Association, 2016) Bronstein, Michael; Kalogerakis, Evangelos; Rodola, Emanuele; Masci, Jonathan; Boscaini, Davide; Augusto Sousa and Kadi BouatouchThe past decade in computer vision research has witnessed the re-emergence of deep learning, and in particular convolutional neural network (CNN) techniques, allowing to learn powerful image feature representations from large collections of examples. Nevertheless, when attempting to apply standard deep learning methods to geometric data which by its nature is non-Euclidean (e.g. 3D shapes, graphs), one has to face fundamental differences between images and geometric objects. The purpose of this tutorial is to overview the foundations and the state of the art on learning techniques for 3D shape analysis. Special focus will be put on deep learning (CNN) applied to Euclidean and non-Euclidean manifolds for tasks of shape classification, retrieval and correspondence. The tutorial will present in a new light the problems of shape analysis, emphasizing the analogies and differences with the classical 2D setting and showing how to adapt popular learning schemes to deal with deformable shapes.Item Lowering the Entry Barrier for Students Programming Virtual Reality Applications(The Eurographics Association, 2016) Lambers, Martin; Beatriz Sousa Santos and Jean-Michel DischlerIn Computer Graphics, it is common practice to accompany lectures with hands-on tutorials and/or project assignments that allow students to write and run their own interactive graphics applications. In the special case of Virtual Reality courses, this approach is difficult to maintain since the software requirements pose a high entry barrier to students. In this paper, we propose a technique to significantly simplify Virtual Reality application programming, and implement it in an easy-to-use framework that supports the full range of typical Virtual Reality hardware setups, from head-mounted displays to multi-node, multi-GPU render clusters. The framework lowers the entry barrier for students and allows them to focus on course goals instead of fighting software complexities.