Search Results

Now showing 1 - 3 of 3
  • 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
    Object Detection and Classification from Large-Scale Cluttered Indoor Scans
    (The Eurographics Association and John Wiley and Sons Ltd., 2014) Mattausch, Oliver; Panozzo, Daniele; Mura, Claudio; Sorkine-Hornung, Olga; Pajarola, Renato; B. Levy and J. Kautz
    We present a method to automatically segment indoor scenes by detecting repeated objects. Our algorithm scales to datasets with 198 million points and does not require any training data. We propose a trivially parallelizable preprocessing step, which compresses a point cloud into a collection of nearly-planar patches related by geometric transformations. This representation enables us to robustly filter out noise and greatly reduces the computational cost and memory requirements of our method, enabling execution at interactive rates. We propose a patch similarity measure based on shape descriptors and spatial configurations of neighboring patches. The patches are clustered in a Euclidean embedding space based on the similarity matrix to yield the segmentation of the input point cloud. The generated segmentation can be used to compress the raw point cloud, create an object database, and increase the clarity of the point cloud visualization.
  • Item
    Content-Aware Surface Parameterization for Interactive Restoration of Historical Documents
    (The Eurographics Association and John Wiley and Sons Ltd., 2014) Pal, Kazim; Schüller, Christian; Panozzo, Daniele; Sorkine-Hornung, Olga; Weyrich, Tim; B. Levy and J. Kautz
    We present an interactive method to restore severely damaged historical parchments. When damaged by heat in a fire, such manuscripts undergo a complex deformation and contain various geometric distortions such as wrinkling, buckling, and shrinking, rendering them nearly illegible. They cannot be physically flattened due to the risk of further damage. We propose a virtual restoration framework to estimate the non-rigid deformation the parchment underwent and to revert it, making reading the text significantly easier whilst maintaining the veracity of the textual content. We estimate the deformation by combining automatically extracted constraints with user-provided hints informed by domain knowledge. We demonstrate that our method successfully flattens and straightens the text on a variety of pages scanned from a 17th century document which fell victim to fire damage.