Path-space differentiable rendering
It is shown how path integrals can be differentiated with respect to arbitrary differentiable changes of a scene and 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 are considered.
Abstract
<jats:p>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.</jats:p> <jats:p>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.</jats:p> <jats:p>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.</jats:p>