Browsing VMV2021 by Subject "Computing methodologies"

Now showing items 1-5 of 5

    • Capturing Anisotropic SVBRDFs 

      Kaltheuner, Julian; Bode, Lukas; Klein, Reinhard (The Eurographics Association, 2021)
      In this work, we adapt and improve recent isotropic material estimation efforts to estimate spatially varying anisotropic materials with an additional Fresnel term using a variable set of input images and are able to handle ...

    • EMCA: Explorer of Monte Carlo based Algorithms 

      Ruppert, Lukas; Kreisl, Christoph; Blank, Nils; Herholz, Sebastian; Lensch, Hendrik P. A. (The Eurographics Association, 2021)
      Debugging or analyzing the performance of global illumination algorithms is a challenging task due to the complex path-scene interaction and numerous places where errors and programming bugs can occur. We present a novel, ...

    • FERMIUM: A Framework for Real-time Procedural Point Cloud Animation and Morphing 

      Wegen, Ole; Böttger, Florence; Döllner, Jürgen; Trapp, Matthias (The Eurographics Association, 2021)
      This paper presents a framework for generating real-time procedural animations and morphing of 3D point clouds. Point clouds or point-based geometry of varying density can easily be acquired using LiDAR cameras or modern ...

    • Real-Time Curvature-aware Re-Parametrization and Tessellation of Bézier Surfaces 

      Buchenau, Christoph; Guthe, Michael (The Eurographics Association, 2021)
      Interactive tessellation of parametric surfaces has many applications in both engineering and entertainment computing. The most common primitives are bi-cubic Bézier patches which are, among others, an intermediate ...

    • SuBloNet: Sparse Super Block Networks for Large Scale Volumetric Fusion 

      Rückert, Darius; Stamminger, Marc (The Eurographics Association, 2021)
      Training and inference of convolutional neural networks (CNNs) on truncated signed distance fields (TSDFs) is a challenging task. Large parts of the scene are usually empty, which makes dense implementations inefficient ...