Search Results

Now showing 1 - 10 of 106
  • Item
    Dynamic 2D/3D Registration
    (The Eurographics Association, 2014) Bouaziz, Sofien; Tagliasacchi, Andrea; Pauly, Mark; Nicolas Holzschuch and Karol Myszkowski
    Image and geometry registration algorithms are an essential component of many computer graphics and computer vision systems. With recent technological advances in RGB-D sensors, such as the Microsoft Kinect or Asus Xtion Live, robust algorithms that combine 2D image and 3D geometry registration have become an active area of research. The goal of this course is to introduce the basics of 2D/3D registration algorithms and to provide theoretical explanations and practical tools to design computer vision and computer graphics systems based on RGB-D devices. To illustrate the theory and demonstrate practical relevance, we briefly discuss three applications: rigid scanning, non-rigid modeling, and realtime face tracking. Our course targets researchers and computer graphics practitioners with a background in computer graphics and/or computer vision. An up-to-date version of the course notes as well as slides and source code can be found at http://lgg.epfl.ch/2d3dRegistration.
  • Item
    Post-Tessellation Geometry Caches
    (The Eurographics Association, 2014) Sathe, Rahul; Foley, Tim; Salvi, Marco; Eric Galin and Michael Wand
    Current 3D rendering architectures support adaptive tessellation of patches, allowing for increased geometric detail. Patches are specified independently, giving the implementation freedom to exploit parallel execution. However, this independence leads to redundant shading computations at patch corners and along edges. In this paper, we present post-tessellation geometry caches, the edge cache and corner cache, that can reduce redundant shading along patch edges and corners, respectively. We demonstrate the two caches in a software-simulated D3D11 rendering pipeline, and show that for current tessellation workloads our approach saves up to 37% of post-tessellation vertex shading using caches with as few as 8 entries.
  • Item
    Efficient Sorting and Searching in Rendering Algorithms
    (The Eurographics Association, 2014) Havran, Vlastimil; Bittner, Jiri; Nicolas Holzschuch and Karol Myszkowski
    In the tutorial we show the connection between rendering algorithms and sorting and searching as classical problems studied in computer science. We provide both theoretical and empirical evidence that for many rendering techniques most time is spent by sorting and searching. In particular we discuss problems and solutions for visibility computation, density estimation, and importance sampling. For each problem we mention its specific issues such as dimensionality of the search domain or online versus offline searching. We will present the underlying data structures and their enhancements in the context of specific rendering algorithms such as ray tracing, photon mapping, and hidden surface removal.
  • Item
    The Four I's Recipe for Cooking Up Computer Graphics Exercises and Assessments
    (The Eurographics Association, 2014) Peters, Christopher E.; Anderson, Eike Falk; Jean-Jacques Bourdin and Joaquim Jorge and Eike Anderson
    The design of meaningful student activities, such as lab exercises and assignments, is a core element of computer graphics pedagogy. Here, we briefly describe our efforts towards making the process of defining and structuring computer graphics activities more explicit. We focus on four main activity categories that are building blocks for practical course design: Independent, Iterative, Incremental and Integrative. These ``Four I's'' of computer graphics activity provide the fundamental ingredients for explicitly defining the design of activity-oriented computer graphics courses with the potential to deliver significant artefacts that may, for example, constitute a portfolio of work for assessment or presentation to employers. The categorisations are intended as the first steps towards more clearly structuring and communicating exercise specifications in collaborative course development settings.
  • Item
    Accurate and Efficient Lighting for Skinned Models
    (The Eurographics Association and John Wiley and Sons Ltd., 2014) Tarini, Marco; Panozzo, Daniele; Sorkine-Hornung, Olga; B. Levy and J. Kautz
    In the context of real-time, GPU-based rendering of animated skinned meshes, we propose a new algorithm to compute surface normals with minimal overhead both in terms of the memory footprint and the required per-vertex operations. By accounting for the variation of the skinning weights over the surface, we achieve a higher visual quality compared to the standard approximation ubiquitously used in video-game engines and other real-time applications. Our method supports Linear Blend Skinning and Dual Quaternion Skinning. We demonstrate the advantages of our technique on a variety of datasets and provide a complete open-source implementation, including GLSL shaders.
  • Item
    Optimizing Stereo-to-Multiview Conversion for Autostereoscopic Displays
    (The Eurographics Association and John Wiley and Sons Ltd., 2014) Chapiro, Alexandre; Heinzle, Simon; Aydin, Tunç Ozan; Poulakos, Steven; Zwicker, Matthias; Smolic, Aljosa; Gross, Markus; B. Levy and J. Kautz
    We present a novel stereo-to-multiview video conversion method for glasses-free multiview displays. Different from previous stereo-to-multiview approaches, our mapping algorithm utilizes the limited depth range of autostereoscopic displays optimally and strives to preserve the scene s artistic composition and perceived depth even under strong depth compression. We first present an investigation of how perceived image quality relates to spatial frequency and disparity. The outcome of this study is utilized in a two-step mapping algorithm, where we (i) compress the scene depth using a non-linear global function to the depth range of an autostereoscopic display, and (ii) enhance the depth gradients of salient objects to restore the perceived depth and salient scene structure. Finally, an adapted image domain warping algorithm is proposed to generate the multiview output, which enables overall disparity range extension.
  • Item
    CSG Feature Trees from Engineering Sketches of Polyhedral Shapes
    (The Eurographics Association, 2014) Plumed, Raquel; Company, Pedro; Varley, Peter A. C.; Martin, Ralph R.; Eric Galin and Michael Wand
    We give a method to obtain a 3D CSG model from a 2D engineering wireframe sketch which depicts a polyhedral shape. The method finds a CSG feature tree compatible with a reverse design history of a 2D line-drawing obtained by vectorising the sketch. The process used seeks the CSG feature tree recursively, combining all design or manufacturing features embedded in the sketch, proceeding in reverse order from the most detailed features to the blank.
  • Item
    Interactive Motion Mapping for Real-time Character Control
    (The Eurographics Association and John Wiley and Sons Ltd., 2014) Rhodin, Helge; Tompkin, James; Kim, Kwang In; Varanasi, Kiran; Seidel, Hans-Peter; Theobalt, Christian; B. Levy and J. Kautz
    Abstract It is now possible to capture the 3D motion of the human body on consumer hardware and to puppet in real time skeleton-based virtual characters. However, many characters do not have humanoid skeletons. Characters such as spiders and caterpillars do not have boned skeletons at all, and these characters have very different shapes and motions. In general, character control under arbitrary shape and motion transformations is unsolved - how might these motions be mapped? We control characters with a method which avoids the rigging-skinning pipeline - source and target characters do not have skeletons or rigs. We use interactively-defined sparse pose correspondences to learn a mapping between arbitrary 3D point source sequences and mesh target sequences. Then, we puppet the target character in real time. We demonstrate the versatility of our method through results on diverse virtual characters with different input motion controllers. Our method provides a fast, flexible, and intuitive interface for arbitrary motion mapping which provides new ways to control characters for real-time animation.
  • Item
    Coded Exposure HDR Light-Field Video Recording
    (The Eurographics Association and John Wiley and Sons Ltd., 2014) Schedl, David C.; Birklbauer, Clemens; Bimber, Oliver; B. Levy and J. Kautz
    Capturing exposure sequences to compute high dynamic range (HDR) images causes motion blur in cases of camera movement. This also applies to light-field cameras: frames rendered from multiple blurred HDR lightfield perspectives are also blurred. While the recording times of exposure sequences cannot be reduced for a single-sensor camera, we demonstrate how this can be achieved for a camera array. Thus, we decrease capturing time and reduce motion blur for HDR light-field video recording. Applying a spatio-temporal exposure pattern while capturing frames with a camera array reduces the overall recording time and enables the estimation of camera movement within one light-field video frame. By estimating depth maps and local point spread functions (PSFs) from multiple perspectives with the same exposure, regional motion deblurring can be supported. Missing exposures at various perspectives are then interpolated.
  • Item
    Latency Considerations of Depth-first GPU Ray Tracing
    (The Eurographics Association, 2014) Guthe, Michael; Eric Galin and Michael Wand
    Despite the potential divergence of depth-first ray tracing [AL09], it is nevertheless the most efficient approach on massively parallel graphics processors. Due to the use of specialized caching strategies that were originally developed for texture access, it has been shown to be compute rather than bandwidth limited. Especially with recents developments however, not only the raw bandwidth, but also the latency for both memory access and read after write register dependencies can become a limiting factor. In this paper we will analyze the memory and instruction dependency latencies of depth first ray tracing. We will show that ray tracing is in fact latency limited on current GPUs and propose three simple strategies to better hide the latencies. This way, we come significantly closer to the maximum performance of the GPU.