Efficient Differentiation of Pixel Reconstruction Filters for Path-Space Differentiable Rendering

  • Zihan Yu
  • , Cheng Zhang
  • , Derek Nowrouzezahrai
  • , Zhao Dong
  • , Shuang Zhao

Research output: Contribution to journalArticlepeer-review

Abstract

Pixel reconstruction filters play an important role in physics-based rendering and have been thoroughly studied. In physics-based differentiable rendering, however, the proper treatment of pixel filters remains largely under-explored. We present a new technique to efficiently differentiate pixel reconstruction filters based on the path-space formulation. Specifically, we formulate the pixel boundary integral that models discontinuities in pixel filters and introduce new antithetic sampling methods that support differentiable path sampling methods, such as adjoint particle tracing and bidirectional path tracing. We demonstrate both the need and efficacy of antithetic sampling when estimating this integral, and we evaluate its effectiveness across several differentiable- and inverse-rendering settings.

Original languageEnglish (US)
Article number191
JournalACM Transactions on Graphics
Volume41
Issue number6
Early online dateNov 30 2022
DOIs
StatePublished - Nov 30 2022
Externally publishedYes

Keywords

  • differentiable rendering
  • differential path integral
  • pixel reconstruction filter

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Efficient Differentiation of Pixel Reconstruction Filters for Path-Space Differentiable Rendering'. Together they form a unique fingerprint.

Cite this