Path-Space Differentiable Rendering
| Cheng Zhang | Bailey Miller | Kai Yan | Ioannis Gkioulekas | Shuang Zhao |
ACM Trans. Graph. (2020)
Physics-based differentiable rendering, the estimation of derivatives of radiometric measures with respect to arbitrary scene parameters, has a diverse array of applications from solving analysis-by-synthesis problems to training machine learning pipelines incorporating forward rendering processes. Unfortunately, general-purpose differentiable rendering remains challenging due to the lack of efficient estimators as well as the need to identify and handle complex discontinuities such as visibility boundaries. In this paper, we show how path integrals can be differentiated with respect to arbitrary differentiable changes of a scene. We provide a detailed theoretical analysis of this process and establish new differentiable rendering formulations based on the resulting differential path integrals. Our path-space differentiable rendering formulation allows the design of new Monte Carlo estimators that offer significantly better efficiency than state-of-the-art methods in handling complex geometric discontinuities and light transport phenomena such as caustics. We validate our method by comparing our derivative estimates to those generated using the finite-difference method. To demonstrate the effectiveness of our technique, we compare inverse-rendering performance with a few state-of-the-art differentiable rendering methods.
Cheng Zhang, Bailey Miller, Kai Yan, Ioannis Gkioulekas, Shuang Zhao (2020). Path-Space Differentiable Rendering. ACM Trans. Graph..
@article{Zhang:2020:PSDR,
author = {Cheng Zhang and Bailey Miller and Kai Yan and Ioannis Gkioulekas and Shuang Zhao},
title = {Path-Space Differentiable Rendering},
journal = {ACM Trans. Graph.},
year = {2020},
publisher = {ACM},
address = {New York, NY, USA},
}
