Joint Neural Denoising of Surfaces and Volumes

Hofmann N, Hasselgren J, Munkberg J (2023)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Conference Proceedings Title: Proceedings of the ACM on Computer Graphics and Interactive Techniques

Event location: Bellevue, WA, United States US


DOI: 10.1145/3585497


Denoisers designed for surface geometry rely on noise-free feature guides for high quality results. However, these guides are not readily available for volumes. Our method enables combined volume and surface denoising in real time from low sample count (4 spp) renderings. The rendered image is decomposed into volume and surface layers, leveraging spatio-temporal neural denoisers for both components. The individual signals are composited using learned weights and denoised transmittance. Our architecture outperforms current denoisers in scenes containing both surfaces and volumes, and produces temporally stable results at interactive rates.

Authors with CRIS profile

Involved external institutions

How to cite


Hofmann, N., Hasselgren, J., & Munkberg, J. (2023). Joint Neural Denoising of Surfaces and Volumes. In Proceedings of the ACM on Computer Graphics and Interactive Techniques. Bellevue, WA, United States, US.


Hofmann, Nikolai, Jon Hasselgren, and Jacob Munkberg. "Joint Neural Denoising of Surfaces and Volumes." Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, Bellevue, WA, United States 2023.

BibTeX: Download