Recursive Control Variates for Inverse Rendering

doi:10.1145/3592139

Recursive Control Variates for Inverse Rendering

2023-07-26

14

OA

AI

DOI：10.1145/3592139

Original request for help

Save

Abstract

En 中文

We present a method for reducing errors-variance and bias-in physically based differentiable rendering (PBDR). Typical applications of PBDR repeatedly render a scene as part of an optimization loop involving gradient descent. The actual change introduced by each gradient descent step is often relatively small, causing a significant degree of redundancy in this computation. We exploit this redundancy by formulating a gradient estimator that employs a recursive control variate, which leverages information from previous optimization steps. The control variate reduces variance in gradients, and, perhaps more importantly, alleviates issues that arise from differentiating loss functions with respect to noisy inputs, a common cause of drift to bad local minima or divergent optimizations. We experimentally evaluate our approach on a variety of path-traced scenes containing surfaces and volumes and observe that primal rendering efficiency improves by a factor of up to 10.

Keywords:

Differentiable rendering

control variates

Recursive Control Variates for Inverse Rendering

Abstract

Journal

Organization