Patent · US Active

Denoising Monte Carlo renderings using neural networks with asymmetric loss

US10699382B2 · kind B2 · utility

5Cited by
3References
20Claims
0Family size

Assignees

Inventors

Key dates

Filing dateJul 31, 2018
Grant dateJun 30, 2020
Priority date
Expiry dateNov 15, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20182
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.