BIROn - Birkbeck Institutional Research Online

    Neural bounding

    Liu, S.W. and Fischer, M. and Yoo, Paul and Ritschel, T. (2024) Neural bounding. ACM SIGGRAPH 2024 Conference ,

    [img] Text
    3641519.3657442.pdf - Published Version of Record
    Restricted to Repository staff only

    Download (32MB)

    Abstract

    Bounding volumes are an established concept in computer graphics and vision tasks but have seen little change since their early inception. In this work, we study the use of neural networks as bounding volumes. Our key observation is that bounding, which so far has primarily been considered a problem of computational geometry, can be redefined as a problem of learning to classify space into free or occupied. This learning-based approach is particularly advantageous in high-dimensional spaces, such as animated scenes with complex queries, where neural networks are known to excel. However, unlocking neural bounding requires a twist: allowing – but also limiting – false positives, while ensuring that the number of false negatives is strictly zero. We enable such tight and conservative results using a dynamically-weighted asymmetric loss function. Our results show that our neural bounding produces up to an order of magnitude fewer false positives than traditional methods. In addition, we propose an extension of our bounding method using early exits that accelerates query speeds by 25 %. We also demonstrate that our approach is applicable to non-deep learning models that train within seconds. Our project page is at https://wenxin-liu.github.io/neural_bounding/.

    Metadata

    Item Type: Article
    Additional Information: SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference, Denver CO USA, 27 July 2024- 1 August 2024. ISBN: 9798400705250
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Depositing User: Paul Yoo
    Date Deposited: 15 Jul 2024 13:11
    Last Modified: 16 Jul 2024 00:02
    URI: https://eprints.bbk.ac.uk/id/eprint/53824

    Statistics

    Activity Overview
    6 month trend
    1Download
    6 month trend
    116Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item
    Edit/View Item