Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering
Name
3680528.3687622.pdf
Size
4.09 MB
Format
Adobe PDF
Checksum (MD5)
577b183198dffda3366112d43869bc67
Author(s)
Xu, Peiyu
Bangaru, Sai
Li, Tzu-Mao
Zhao, Shuang
Date Issued
December 3, 2024
Publisher
ACM|SIGGRAPH Asia 2024 Conference Papers
Citation
Xu, Peiyu, Bangaru, Sai, Li, Tzu-Mao and Zhao, Shuang. 2024. "Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering."
Version
Final published version
Abstract
Physics-based differentiable rendering requires estimating boundary path integrals emerging from the shift of discontinuities (e.g., visibility boundaries). Previously, although the mathematical formulation of boundary path integrals has been established, efficient and robust estimation of these integrals has remained challenging. Specifically, state-of-the-art boundary sampling methods all rely on primary-sample-space guiding precomputed using sophisticated data structures—whose performance tends to degrade for finely tessellated geometries.
In this paper, we address this problem by introducing a new Markov-Chain-Monte-Carlo (MCMC) method. At the core of our technique is a local perturbation step capable of efficiently exploring highly fragmented primary sample spaces via specifically designed jumping rules. We compare the performance of our technique with several state-of-the-art baselines using synthetic differentiable-rendering and inverse-rendering experiments.
Description
SA Conference Papers ’24, December 03–06, 2024, Tokyo, Japan
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3680528.3687622
