Antithetic Sampling for Monte Carlo Differentiable Rendering

Cheng Zhang, Zhao Dong, Michael Doggett, Shuang Zhao

Research output: Contribution to journalArticlepeer-review

8 Citations (SciVal)

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.
Original languageEnglish
Article number77
Pages (from-to)1
Number of pages12
JournalACM Transactions on Graphics
Volume40
Issue number4
DOIs
Publication statusPublished - 2021 Jul 19

Subject classification (UKÄ)

  • Other Computer and Information Science

Keywords

  • Computer Graphics
  • Path Tracing

Fingerprint

Dive into the research topics of 'Antithetic Sampling for Monte Carlo Differentiable Rendering'. Together they form a unique fingerprint.

Cite this