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.
@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", 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." }