• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Conferences
    • EG2017
    • EG 2017 - Short Papers
    • View Item
    •   Eurographics DL Home
    • Eurographics Conferences
    • EG2017
    • EG 2017 - Short Papers
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Ambient Occlusion Baking via a Feed-Forward Neural Network

    Thumbnail
    View/Open
    013-016.pdf (940.2Kb)
    ao_baking_via_neural_network.zip (51.51Mb)
    neuralnetwork.mp4 (89.95Mb)
    Date
    2017
    Author
    Erra, Ugo ORCID
    Capece, Nicola Felice ORCID
    Agatiello, Roberto
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    We present a feed-forward neural network approach for ambient occlusion baking in real-time rendering. The idea is based on implementing a multi-layer perceptron that allows a general encoding via regression and an efficient decoding via a simple GPU fragment shader. The non-linear nature of multi-layer perceptrons makes them suitable and effective for capturing nonlinearities described by ambient occlusion values. A multi-layer perceptron is also random-accessible, has a compact size, and can be evaluated efficiently on the GPU. We illustrate our approach of screen-space ambient occlusion based on neural network including its quality, size, and run-time speed.
    BibTeX
    @inproceedings {10.2312:egsh.20171003,
    booktitle = {EG 2017 - Short Papers},
    editor = {Adrien Peytavie and Carles Bosch},
    title = {{Ambient Occlusion Baking via a Feed-Forward Neural Network}},
    author = {Erra, Ugo and Capece, Nicola Felice and Agatiello, Roberto},
    year = {2017},
    publisher = {The Eurographics Association},
    ISSN = {1017-4656},
    DOI = {10.2312/egsh.20171003}
    }
    URI
    http://dx.doi.org/10.2312/egsh.20171003
    https://diglib.eg.org:443/handle/10.2312/egsh20171003
    Collections
    • EG 2017 - Short Papers

    Eurographics Association copyright © 2013 - 2023 
    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

    Statistics

    View Usage Statistics

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2023 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA