Joint Neural Denoising of Surfaces and Volumes
Open Access
- 12 May 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 6 (1) , 1-16
Abstract
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.Keywords
This publication has 19 references indexed in Scilit:
- Denoising with kernel prediction and asymmetric loss functionsACM Transactions on Graphics, 2018
- Monte Carlo Methods for Volumetric Light Transport SimulationComputer Graphics Forum, 2018
- Kernel-predicting convolutional networks for denoising Monte Carlo renderingsACM Transactions on Graphics, 2017
- Shaping the future through innovations: From medical imaging to precision medicineMedical Image Analysis, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Residual ratio tracking for estimating attenuation in participating mediaACM Transactions on Graphics, 2014
- Integral formulation of null-collision Monte Carlo algorithmsJournal of Quantitative Spectroscopy and Radiative Transfer, 2013
- VDBACM Transactions on Graphics, 2013
- HypertextureACM SIGGRAPH Computer Graphics, 1989
- Diffuse radiation in the GalaxyThe Astrophysical Journal, 1941