EG 2020 - Posters

Permanent URI for this collection

Posters
An End-to-end Framework for 3D Capture and Human Digitization with a Single RGB Camera
Luiz José Schirmer Silva, Djalma S. da Silva, Luiz Velho, and Hélio Lopes
Fabric Appearance Benchmark
Sebastian Merzbach and Reinhard Klein
Streamlining Photogrammetry Reconstructions of Bone Fragments for Bioarchaeological Analysis, Conservation, and Public Engagement
Adam Redford, Richard Mikulski, and Eike Falk Anderson
Integrating Local Collision Avoidance with Shortest Path Maps
Ritesh Sharma, Renato Farias, and Marcelo Kallmann
GPU-Accelerated Generation of the Molecular Surface
Mousa Alhazzazi, Steven Hayward, and Stephen D. Laycock

Browse

Recent Submissions

Now showing 1 - 6 of 6
  • Item
    An End-to-end Framework for 3D Capture and Human Digitization with a Single RGB Camera
    (The Eurographics Association, 2020) Silva, Luiz José Schirmer; Silva, Djalma S. da; Velho, Luiz; Lopes, Hélio; Ritschel, Tobias and Eilertsen, Gabriel
    We present a low cost and accessible end-to-end framework for 3D modeling and texture capture of Humans using deep neural networks and a single RGB camera. We generate a texture atlas considering a set of multi-view images. We also capture data to generate 3D shape models and finally combine it with the generated textures to obtain a full 3D reconstruction of the human body that can be used in a game engine.
  • Item
    Fabric Appearance Benchmark
    (The Eurographics Association, 2020) Merzbach, Sebastian; Klein, Reinhard; Ritschel, Tobias and Eilertsen, Gabriel
    Appearance modeling is a difficult problem that still receives considerable attention from the graphics and vision communities. Though recent years have brought a growing number of high-quality material databases that have sparked new research, there is a general lack of evaluation benchmarks for performance assessment and fair comparisons between competing works. We therefore release a new dataset and pose a public challenge that will enable standardized evaluations. For this we measured 56 fabric samples with a commercial appearance scanner. We publish the resulting calibrated HDR images, along with baseline SVBRDF fits. The challenge is to recreate, under known light and view sampling, the appearance of a subset of unseen images. User submissions will be automatically evaluated and ranked by a set of standard image metrics.
  • Item
    Streamlining Photogrammetry Reconstructions of Bone Fragments for Bioarchaeological Analysis, Conservation, and Public Engagement
    (The Eurographics Association, 2020) Redford, Adam; Mikulski, Richard; Anderson, Eike Falk; Ritschel, Tobias and Eilertsen, Gabriel
    We present a streamlined workflow for the 3D reconstruction of skeletal fragments, suitable for bioarchaeological analysis as well as public engagement and based on practices and applications from the feature film visual effects industry. Using a lowcost single-camera photogrammetry rig for close range photogrammetry and processing the results using standard 3D asset creation software from the visual effects industry, the resulting 3D models achieve a resolution that is sufficient for the clear representation of bone elements and any gross changes affecting them, such as severe trauma.
  • Item
    Integrating Local Collision Avoidance with Shortest Path Maps
    (The Eurographics Association, 2020) Sharma, Ritesh; Farias, Renato; Kallmann, Marcelo; Ritschel, Tobias and Eilertsen, Gabriel
    The effective integration of local collision avoidance with global path planning becomes a necessity when multi-agent systems need to be simulated in complex cluttered environments. This work presents our first results exploring the new approach of integrating Shortest Path Maps (SPMs) with local collision avoidance in order to provide optimal paths for agents to navigate around obstacles toward their goal locations. Our GPU-based SPM implementation is available.
  • Item
    EUROGRAPHICS 2020: Posters Frontmatter
    (Eurographics Association, 2020) Ritschel, Tobias; Eilertsen, Gabriel; Ritschel, Tobias and Eilertsen, Gabriel
  • Item
    GPU-Accelerated Generation of the Molecular Surface
    (The Eurographics Association, 2020) Alhazzazi, Mousa; Hayward, Steven; Laycock, Stephen D.; Ritschel, Tobias and Eilertsen, Gabriel
    A variety of visualisation methods have been developed for displaying molecular structures. The solvent-excluded surface (SES) or molecular surface is one of the most popular and useful depictions as it helps to identify binding-site cavities. The molecular surface is particularly useful therefore for interactive molecular docking tools. Docking tools that incorporate molecular flexibility bring new challenges as the molecular surface must be recomputed in real time as the molecule changes shape in interaction with a ligand. Here we compute the SES by using a GPU-accelerated Marching Cubes algorithm which promises to lead to real-time surface generation for small- to medium-sized biomolecules undergoing conformational change.