Antithetic Sampling for Monte Carlo Differentiable Rendering

PubDate: August 9, 2021

Teams: University of California；Facebook Reality Labs；Lund University

Writers: Cheng Zhang, Zhao Dong, Michael Doggett, Shuang Zhao

PDF: Antithetic Sampling for Monte Carlo Differentiable Rendering

Abstract

Stochastic sampling of light transport paths is key to Monte Carlo forward rendering, and previous studies have led to mature techniques capable of drawing high-contribution light paths in complex scenes. These sampling techniques have also been applied to differentiable rendering.

In this paper, we demonstrate that path sampling techniques developed for forward rendering can become inefficient for differentiable rendering of glossy materials—especially when estimating derivatives with respect to global scene geometries. To address this problem, we introduce antithetic sampling of BSDFs and light-transport paths, allowing significantly faster convergence and can be easily integrated into existing differentiable rendering pipelines. We validate our method by comparing our derivative estimates to those generated with existing unbiased techniques. Further, we demonstrate the effectiveness of our technique by providing equal-quality and equal-time comparisons with existing sampling methods.