Patent · US Active

Machine learning to process Monte Carlo rendered images

US10192146B2 · kind B2 · utility

9Cited by

0References

10Claims

0Family size

Assignee

The Regents of the University of California · US

Inventors

Pradeep Sen · Goleta, US
Steve Bako · Lompoc, US
Nima Khademi Kalantari · San Diego, US

Key dates

Filing date	Dec 13, 2017
Grant date	Jan 29, 2019
Priority date	—
Expiry date	Dec 13, 2037

Classification

Technology area (CPC G)Physics
CPC primaryG06T2207/20084
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

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