• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Workshops and Symposia
    • SCA: Eurographics/SIGGRAPH Symposium on Computer Animation
    • SCA 19: Eurographics/SIGGRAPH Symposium on Computer Animation
    • View Item
    •   Eurographics DL Home
    • Eurographics Workshops and Symposia
    • SCA: Eurographics/SIGGRAPH Symposium on Computer Animation
    • SCA 19: Eurographics/SIGGRAPH Symposium on Computer Animation
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Subspace Neural Physics: Fast Data-Driven Interactive Simulation

    Thumbnail
    View/Open
    06-08-holden.pdf (10.50Mb)
    deepclothsca.mp4 (178.7Mb)
    Date
    2019
    Author
    Holden, Daniel
    Duong, Bang Chi
    Datta, Sayantan
    Nowrouzezahrai, Derek
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    Data-driven methods for physical simulation are an attractive option for interactive applications due to their ability to trade precomputation and memory footprint in exchange for improved runtime performance. Yet, existing data-driven methods fall short of the extreme memory and performance constraints imposed by modern interactive applications like AAA games and virtual reality. Here, performance budgets for physics simulation range from tens to hundreds of micro-seconds per frame, per object. We present a data-driven physical simulation method that meets these constraints. Our method combines subspace simulation techniques with machine learning which, when coupled, enables a very efficient subspace-only physics simulation that supports interactions with external objects - a longstanding challenge for existing subspace techniques. We also present an interpretation of our method as a special case of subspace Verlet integration, where we apply machine learning to efficiently approximate the physical forces of the system directly in the subspace. We propose several practical solutions required to make effective use of such a model, including a novel training methodology required for prediction stability, and a GPU-friendly subspace decompression algorithm to accelerate rendering.
    BibTeX
    @inproceedings {09486.3340245,
    booktitle = {Eurographics/ ACM SIGGRAPH Symposium on Computer Animation},
    editor = {Batty, Christopher and Huang, Jin},
    title = {{Subspace Neural Physics: Fast Data-Driven Interactive Simulation}},
    author = {Holden, Daniel and Duong, Bang Chi and Datta, Sayantan and Nowrouzezahrai, Derek},
    year = {2019},
    publisher = {ACM},
    ISSN = {1727-5288},
    ISBN = {978-1-4503-6677-9},
    DOI = {10.1145/3309486.3340245}
    }
    URI
    https://doi.org/10.1145/3309486.3340245
    https://diglib.eg.org:443/handle/10.1145/3309486-3340245
    Collections
    • SCA 19: Eurographics/SIGGRAPH Symposium on Computer Animation

    Eurographics Association copyright © 2013 - 2020 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA
     

     

    Browse

    All of Eurographics DLCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2020 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA