Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering
SA Conference Papers ’24, December 03–06, 2024, Tokyo, Japan
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM|SIGGRAPH Asia 2024 Conference Papers
2025
|
| Online Access: | https://hdl.handle.net/1721.1/158126 |
| _version_ | 1824458273364901888 |
|---|---|
| author | Xu, Peiyu Bangaru, Sai Li, Tzu-Mao Zhao, Shuang |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Xu, Peiyu Bangaru, Sai Li, Tzu-Mao Zhao, Shuang |
| author_sort | Xu, Peiyu |
| collection | MIT |
| description | SA Conference Papers ’24, December 03–06, 2024, Tokyo, Japan |
| first_indexed | 2025-02-19T04:23:16Z |
| format | Article |
| id | mit-1721.1/158126 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:23:16Z |
| publishDate | 2025 |
| publisher | ACM|SIGGRAPH Asia 2024 Conference Papers |
| record_format | dspace |
| spelling | mit-1721.1/1581262025-02-13T19:20:50Z Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering Xu, Peiyu Bangaru, Sai Li, Tzu-Mao Zhao, Shuang Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory SA Conference Papers ’24, December 03–06, 2024, Tokyo, Japan 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. 2025-01-29T18:28:06Z 2025-01-29T18:28:06Z 2024-12-03 2025-01-01T08:50:36Z Article http://purl.org/eprint/type/ConferencePaper 979-8-4007-1131-2 https://hdl.handle.net/1721.1/158126 Xu, Peiyu, Bangaru, Sai, Li, Tzu-Mao and Zhao, Shuang. 2024. "Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering." PUBLISHER_CC en https://doi.org/10.1145/3680528.3687622 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The author(s) application/pdf ACM|SIGGRAPH Asia 2024 Conference Papers Association for Computing Machinery |
| spellingShingle | Xu, Peiyu Bangaru, Sai Li, Tzu-Mao Zhao, Shuang Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering |
| title | Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering |
| title_full | Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering |
| title_fullStr | Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering |
| title_full_unstemmed | Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering |
| title_short | Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering |
| title_sort | markov chain monte carlo sampling of visibility boundaries for differentiable rendering |
| url | https://hdl.handle.net/1721.1/158126 |
| work_keys_str_mv | AT xupeiyu markovchainmontecarlosamplingofvisibilityboundariesfordifferentiablerendering AT bangarusai markovchainmontecarlosamplingofvisibilityboundariesfordifferentiablerendering AT litzumao markovchainmontecarlosamplingofvisibilityboundariesfordifferentiablerendering AT zhaoshuang markovchainmontecarlosamplingofvisibilityboundariesfordifferentiablerendering |