Warped-Area Reparameterization of Differential Path Integrals
Author(s)
Xu, Peiyu
Bangaru, Sai
Li, Tzu-Mao
Zhao, Shuang
Date Issued
December 4, 2023
Journal
ACM Transactions on Graphics
Publisher
ACM
Citation
Xu, Peiyu, Bangaru, Sai, Li, Tzu-Mao and Zhao, Shuang. 2023. "Warped-Area Reparameterization of Differential Path Integrals." ACM Transactions on Graphics, 42 (6).
Version
Final published version
Abstract
Physics-based differentiable rendering is becoming increasingly crucial for tasks in inverse rendering and machine learning pipelines. To address discontinuities caused by geometric boundaries and occlusion, two classes of methods have been proposed: 1) the edge-sampling methods that directly sample light paths at the scene discontinuity boundaries, which require nontrivial data structures and precomputation to select the edges, and 2) the reparameterization methods that avoid discontinuity sampling but are currently limited to hemispherical integrals and unidirectional path tracing.
We introduce a new mathematical formulation that enjoys the benefits of both classes of methods. Unlike previous reparameterization work that focused on hemispherical integral, we derive the reparameterization in the path space. As a result, to estimate derivatives using our formulation, we can apply advanced Monte Carlo rendering methods, such as bidirectional path tracing, while avoiding explicit sampling of discontinuity boundaries. We show differentiable rendering and inverse rendering results to demonstrate the effectiveness of our method.
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/10.1145/3618330
