TY - GEN
T1 - Denoising Monte Carlo Renders with Diffusion Models
AU - Vavilala, Vaibhav
AU - Vasanth, Rahul
AU - Forsyth, David
N1 - Publisher Copyright:
© 2024 Owner/Author.
PY - 2024/7/25
Y1 - 2024/7/25
N2 - Physically-based renderings contain Monte-Carlo noise, with variance that increases as the number of rays per pixel decreases. This noise, while zero-mean for good modern renderers, can have heavy tails (most notably, for scenes containing specular or refractive objects). Learned methods for restoring low fidelity renders are highly developed, because suppressing render noise means one can save compute and use fast renders with few rays per pixel. We demonstrate that a diffusion model can denoise low fidelity renders successfully. Furthermore, our method can be conditioned on a variety of natural render information, and this conditioning helps performance. Quantitative experiments show that our method is competitive with SOTA across a range of sampling rates; qualitative evidence suggests that the image prior applied by a diffusion method strongly favors reconstructions that are like real images, with straight shadow boundaries, curved specularities, and no fireflies. In contrast, existing methods that do not rely on image foundation models struggle to generalize when pushed outside the training distribution.
AB - Physically-based renderings contain Monte-Carlo noise, with variance that increases as the number of rays per pixel decreases. This noise, while zero-mean for good modern renderers, can have heavy tails (most notably, for scenes containing specular or refractive objects). Learned methods for restoring low fidelity renders are highly developed, because suppressing render noise means one can save compute and use fast renders with few rays per pixel. We demonstrate that a diffusion model can denoise low fidelity renders successfully. Furthermore, our method can be conditioned on a variety of natural render information, and this conditioning helps performance. Quantitative experiments show that our method is competitive with SOTA across a range of sampling rates; qualitative evidence suggests that the image prior applied by a diffusion method strongly favors reconstructions that are like real images, with straight shadow boundaries, curved specularities, and no fireflies. In contrast, existing methods that do not rely on image foundation models struggle to generalize when pushed outside the training distribution.
KW - Diffusion Models
KW - Monte Carlo Denoising
UR - http://www.scopus.com/inward/record.url?scp=85200726218&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85200726218&partnerID=8YFLogxK
U2 - 10.1145/3641234.3671026
DO - 10.1145/3641234.3671026
M3 - Conference contribution
AN - SCOPUS:85200726218
T3 - Proceedings - SIGGRAPH 2024 Posters
BT - Proceedings - SIGGRAPH 2024 Posters
A2 - Spencer, Stephen N.
PB - Association for Computing Machinery
T2 - SIGGRAPH 2024 Posters
Y2 - 28 July 2024 through 1 August 2024
ER -