Neural network system with temporal feedback for adaptive sampling and denoising of rendered sequences
US11475542B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 17, 2019 |
| Grant date | Oct 18, 2022 |
| Priority date | — |
| Expiry date | Jan 21, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20182
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.