Neural Bounding

TL;DR

This paper introduces neural networks as a new approach to bounding volumes, enabling more accurate and faster classification of space with fewer false positives, especially in high-dimensional scenarios.

Contribution

It redefines bounding volumes as a learning problem, introduces a dynamic loss for conservative classification, and extends the method with early exits for speed.

Findings

Achieves up to ten times fewer false positives than traditional methods.

Accelerates query speeds by 25% using early exit strategies.

Applicable to non-deep learning models with quick training times.

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/.