Show simple item record

dc.contributor.authorMunkberg, Jacoben_US
dc.contributor.authorHasselgren, Jonen_US
dc.contributor.editorDachsbacher, Carsten and Pharr, Matten_US
dc.date.accessioned2020-06-28T15:23:34Z
dc.date.available2020-06-28T15:23:34Z
dc.date.issued2020
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14049
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14049
dc.description.abstractWe propose a novel approach for denoising Monte Carlo path traced images, which uses data from individual samples rather than relying on pixel aggregates. Samples are partitioned into layers, which are filtered separately, giving the network more freedom to handle outliers and complex visibility. Finally the layers are composited front-to-back using alpha blending. The system is trained end-to-end, with learned layer partitioning, filter kernels, and compositing. We obtain similar image quality as recent state-of-the-art sample based denoisers at a fraction of the computational cost and memory requirements.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectComputing methodologies
dc.subjectRay tracing
dc.subjectNeural networks
dc.titleNeural Denoising with Layer Embeddingsen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersDenoising and Filtering
dc.description.volume39
dc.description.number4
dc.identifier.doi10.1111/cgf.14049
dc.identifier.pages1-12


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 39-Issue 4
    Rendering 2020 - Symposium Proceedings

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License