Deep Residual Combiner: A Learned Fusion of Spatial, Temporal, and Multiscale Correlated Pixel Estimates

Simple item page
dc.contributor.authorZhou, Weijie
dc.contributor.authorHughes, Euan
dc.contributor.authorHachisuka, Toshiya
dc.contributor.editorMasia, Belen
dc.contributor.editorThies, Justus
dc.date.accessioned2026-04-21T05:31:37Z
dc.date.available2026-04-21T05:31:37Z
dc.date.issued2026
dc.description.abstractCorrelation-based rendering techniques continue to advance, and efficiently exploiting correlations between pixel estimates has become increasingly important. The deep combiner framework [BHHM20] allows us to fuse independent and correlated pixel estimates but focuses solely on spatial correlations. We propose a generalization of the deep combiner framework, the deep residual combiner, that is designed to exploit correlations across spatial, temporal, and multiscale domains. The deep residual combiner enables robust cross-domain fusion, effectively reducing systematic artifacts and significantly enhancing temporal coherence, both of which are especially important in animation scenarios. We demonstrate the effectiveness of our proposed method through several practical applications, showcasing improvements in temporal stability, visual fidelity, and reduction of residual errors across diverse rendering scenarios compared to prior approaches.
dc.description.number2
dc.description.sectionheadersLight Transport: Sampling, Waves, and Denoising
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume45
dc.identifier.doi10.1111/cgf.70358
dc.identifier.issn1467-8659
dc.identifier.pages14 pages
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70358
dc.identifier.urihttps://doi.org/10.1111/cgf.70358
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.
dc.rightsCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleDeep Residual Combiner: A Learned Fusion of Spatial, Temporal, and Multiscale Correlated Pixel Estimates
Files
Original bundle
Now showing 1 - 5 of 8
Thumbnail Image
Name:
cgf70358.pdf
Size:
35.12 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1168_2_mm1.zip
Size:
345.55 MB
Format:
Zip file
Download
No Thumbnail Available
Name:
paper1168_2_mm2.zip
Size:
72.36 MB
Format:
Zip file
Download
No Thumbnail Available
Name:
paper1168_2_mm3.mp4
Size:
304.84 MB
Format:
Video MP4
Download
No Thumbnail Available
Name:
paper1168_2_mm4.mp4
Size:
273.75 MB
Format:
Video MP4
Download
Collections
45-Issue 2
EG 2026 - Full Papers - CGF 45-Issue 2