An efficient denoising algorithm for global illumination

1Stanford University 2Williams College 3Dartmouth College

In Proceedings of High Performance Graphics, 2017

Teaser
Real-time render with direct light plus two path-traced indirect samples per pixel, and our result denoised in 10 ms.
Abstract Downloads Videos Cite Related

Abstract

We propose a hybrid ray-tracing/rasterization strategy for real- time rendering enabled by a fast new denoising method. We factor global illumination into direct light at rasterized primary surfaces and two indirect lighting terms, each estimated with one path- traced sample per pixel. Our factorization enables efficient (biased) reconstruction by denoising light without blurring materials. We demonstrate denoising in under 10 ms per 1280×720 frame, compare results against the leading offline denoising methods, and include a supplement with source code, video, and data.

Downloads

Videos

Video (full-quality)

Cite

Michael Mara, Morgan McGuire, Benedikt Bitterli, Wojciech Jarosz. An efficient denoising algorithm for global illumination. Proceedings of High Performance Graphics, July 2017. 
@inproceedings{mara17towards,
    author    = {Mara, Michael and McGuire, Morgan and Bitterli, Benedikt and Jarosz, Wojciech},
    title     = {An Efficient Denoising Algorithm for Global Illumination},
    booktitle = {Proceedings of High Performance Graphics},
    year      = {2017},
    month     = jul,
    publisher = {ACM},
    address   = {New York, NY, USA},
    isbn      = {978-1-4503-5101-0},
    location  = {Los Angeles, California, USA},
    doi       = {10/gfzndq}
}
© The Author(s) / ACM. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record is available at doi.acm.org.