CS Talk
Stephanie Wenxin Liu
University College London
Host: Holly Rushmeier
“Neural Bounding”
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/.
Bio:
Stephanie Wenxin Liu recently completed an MSc in Computer Science from Birkbeck, University of London, under the supervision of Prof. Tobias Ritschel at University College London (UCL). Her research focused on the intersection of computer graphics and machine learning, specifically on bounding volumes. Prior to her MSc, Stephanie spent a decade in industry, where she worked as a software engineer and infrastructural engineer, contributing to research, design, and implementation across diverse technical domains. She is currently exploring opportunities for a PhD in computer graphics or vision, with plans to apply in the upcoming cycle. In the interim, she will be working at the Max Planck Institute for Informatics as a research scientist, collaborating with Dr. Thomas Leimkühler on generative AI. Stephanie welcomes discussions with researchers and institutions working in related areas.