Path‐based Monte Carlo Denoising Using a Three‐Scale Neural Network

dc.contributor.authorLin, Weihengen_US
dc.contributor.authorWang, Beibeien_US
dc.contributor.authorYang, Jianen_US
dc.contributor.authorWang, Luen_US
dc.contributor.authorYan, Ling‐Qien_US
dc.contributor.editorBenes, Bedrich and Hauser, Helwigen_US
dc.date.accessioned2021-02-27T19:02:32Z
dc.date.available2021-02-27T19:02:32Z
dc.date.issued2021
dc.description.abstractMonte Carlo rendering is widely used in the movie industry. Since it is costly to produce noise‐free results directly, Monte Carlo denoising is often applied as a post‐process. Recently, deep learning methods have been successfully leveraged in Monte Carlo denoising. They are able to produce high quality denoised results, even with very low sample rate, e.g. 4 spp (sample per pixel). However, for difficult scene configurations, some details could be blurred in the denoised results. In this paper, we aim at preserving more details from inputs rendered with low spp. We propose a novel denoising pipeline that handles three‐scale features ‐ pixel, sample and path ‐ to preserve sharp details, uses an improved Res2Net feature extractor to reduce the network parameters and a smooth feature attention mechanism to remove low‐frequency splotches. As a result, our method achieves higher denoising quality and preserves better details than the previous methods.en_US
dc.description.number1
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume40
dc.identifier.doi10.1111/cgf.14194
dc.identifier.issn1467-8659
dc.identifier.pages369-381
dc.identifier.urihttps://doi.org/10.1111/cgf.14194
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14194
dc.publisher© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltden_US
dc.subjectdeep learning
dc.subjectMonte Carlo denoising
dc.subjectpath‐based
dc.subjectsample‐based
dc.subjectneural network
dc.titlePath‐based Monte Carlo Denoising Using a Three‐Scale Neural Networken_US
Files
Collections