Denoising Monte Carlo Renders with Diffusion Models

Vaibhav Vavilala, Rahul Vasanth, David Forsyth

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Physically-based renderings contain Monte-Carlo noise, with variance that increases as the number of rays per pixel decreases. This noise, while zero-mean for good modern renderers, can have heavy tails (most notably, for scenes containing specular or refractive objects). Learned methods for restoring low fidelity renders are highly developed, because suppressing render noise means one can save compute and use fast renders with few rays per pixel. We demonstrate that a diffusion model can denoise low fidelity renders successfully. Furthermore, our method can be conditioned on a variety of natural render information, and this conditioning helps performance. Quantitative experiments show that our method is competitive with SOTA across a range of sampling rates; qualitative evidence suggests that the image prior applied by a diffusion method strongly favors reconstructions that are like real images, with straight shadow boundaries, curved specularities, and no fireflies. In contrast, existing methods that do not rely on image foundation models struggle to generalize when pushed outside the training distribution.

Original languageEnglish (US)
Title of host publicationProceedings - SIGGRAPH 2024 Posters
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400705168
DOIs
StatePublished - Jul 25 2024
EventSIGGRAPH 2024 Posters - Denver, United States
Duration: Jul 28 2024Aug 1 2024

Publication series

NameProceedings - SIGGRAPH 2024 Posters

Conference

ConferenceSIGGRAPH 2024 Posters
Country/TerritoryUnited States
CityDenver
Period7/28/248/1/24

Keywords

  • Diffusion Models
  • Monte Carlo Denoising

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Denoising Monte Carlo Renders with Diffusion Models'. Together they form a unique fingerprint.

Cite this