{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T11:06:31Z","timestamp":1779275191535,"version":"3.51.4"},"reference-count":87,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN\u20102020\u201003918"],"award-info":[{"award-number":["RGPIN\u20102020\u201003918"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Correlation\u2010based 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\u2010domain 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.<\/jats:p>","DOI":"10.1111\/cgf.70358","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T10:20:08Z","timestamp":1779272408000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Residual Combiner: A Learned Fusion of Spatial, Temporal, and Multiscale Correlated Pixel Estimates"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0294-7623","authenticated-orcid":false,"given":"W.","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Waterloo  Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Hughes","sequence":"additional","affiliation":[{"name":"University of Waterloo  Canada"},{"name":"\u00c9cole de technologie sup\u00e9rieure  Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Hachisuka","sequence":"additional","affiliation":[{"name":"University of Waterloo  Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"e_1_2_13_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3406183"},{"key":"e_1_2_13_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417847"},{"key":"e_1_2_13_3_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3414685.34178471 2 5 7 10 11."},{"key":"e_1_2_13_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530730"},{"key":"e_1_2_13_4_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3528233.35307307."},{"key":"e_1_2_13_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618177"},{"key":"e_1_2_13_5_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3610548.36181777 8."},{"key":"e_1_2_13_6_2","unstructured":"Bitterli Benedikt.Rendering resources.https:\/\/benedikt-bitterli.me\/resources\/.20165 6 8."},{"key":"e_1_2_13_7_2","first-page":"4","volume-title":"Computer Graphics Forum","author":"Bitterli Benedikt","year":"2016"},{"key":"e_1_2_13_8_2","first-page":"125","article-title":"Accelerating Path Tracing by Re-Using Paths","volume":"2","author":"Bekaert Philippe","year":"2002","journal-title":"Rendering Techniques"},{"key":"e_1_2_13_9_2","first-page":"97","article-title":"Kernel-predicting convolutional networks for denoising Monte Carlo renderings","volume":"36","author":"Bako Steve","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_13_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073708"},{"key":"e_1_2_13_10_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3072959.30737083."},{"key":"e_1_2_13_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591562"},{"key":"e_1_2_13_11_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3588432.35915622 3 5 7 8 12."},{"key":"e_1_2_13_12_2","article-title":"Spatiotemporal reservoir resampling for real-time ray tracing with dynamic direct lighting","volume":"39","author":"Bitterli Benedikt","year":"2020","journal-title":"ACM Transactions on Graphics (Proceedings of SIGGRAPH)"},{"key":"e_1_2_13_13_2","unstructured":"Chen Chuhao.mitsuba.https:\/\/github.com\/CzzzzH\/mitsuba\/tree\/79de54dfddc831fda1f54dc7904b3449baf33454.20245."},{"key":"e_1_2_13_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3687938"},{"key":"e_1_2_13_14_3","unstructured":"url:https:\/\/doi.org\/10.1145\/36879387."},{"key":"e_1_2_13_15_2","article-title":"Temporally Stable Metropolis Light Transport Denoising using Recurrent Transformer Blocks","volume":"4","author":"Chen Chuhao","year":"2024","journal-title":"ACM Transactions on Graphics (Proceedings of SIGGRAPH)"},{"key":"e_1_2_13_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073601"},{"key":"e_1_2_13_17_2","unstructured":"Chan Kelvin CK Wang Xintao Xu Xiangyu et al. \u201cBasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment\u201d.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).20224."},{"key":"e_1_2_13_18_2","doi-asserted-by":"crossref","unstructured":"Chan Kelvin CK Wang Xintao Yu Ke et al. \u201cBasicVSR: The Search for Essential Components in Video SuperResolution and Beyond\u201d.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2021 4947\u201349564.","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"e_1_2_13_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480547"},{"key":"e_1_2_13_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2532708"},{"key":"e_1_2_13_20_3","unstructured":"url:https:\/\/doi.org\/10.1145\/25327087."},{"key":"e_1_2_13_21_2","first-page":"2","volume-title":"Computer Graphics Forum","author":"Firmino Arthur","year":"2022"},{"key":"e_1_2_13_22_2","doi-asserted-by":"crossref","unstructured":"Firmino Arthur Frisvad Jeppe Revall andJensen Henrik Wann. \u201cDenoising-aware adaptive sampling for Monte Carlo ray tracing\u201d.ACM SIGGRAPH 2023 Conference Proceedings.2023 1\u2013117.","DOI":"10.1145\/3588432.3591537"},{"key":"e_1_2_13_23_2","doi-asserted-by":"crossref","unstructured":"Firmino Arthur Ramamoorthi Ravi Revall Frisvad Jeppe andWann Jensen Henrik. \u201cPractical error estimation for denoised monte carlo image synthesis\u201d.ACM SIGGRAPH 2024 Conference Papers.2024 1\u2013107.","DOI":"10.1145\/3641519.3657511"},{"key":"e_1_2_13_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555496"},{"key":"e_1_2_13_24_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3550454.35554967."},{"key":"e_1_2_13_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3744898"},{"key":"e_1_2_13_25_3","unstructured":"url:https:\/\/doi.org\/10.1145\/37448987."},{"key":"e_1_2_13_26_2","doi-asserted-by":"crossref","unstructured":"Haris Muhammad Shakhnarovich Gregory andUkita Norimichi. \u201cRecurrent Back-Projection Network for Video Super-Resolution\u201d.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2019 3897\u201339064.","DOI":"10.1109\/CVPR.2019.00402"},{"key":"e_1_2_13_27_2","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume":"2106","author":"Hu Edward J.","year":"2021","journal-title":"CoRR"},{"key":"e_1_2_13_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459793"},{"key":"e_1_2_13_29_2","unstructured":"Jakob Wenzel.Mitsuba renderer.http:\/\/www.mitsuba-renderer.org.20105 6."},{"key":"e_1_2_13_30_2","first-page":"122","article-title":"A machine learning approach for filtering Monte Carlo noise","volume":"34","author":"Kalantari Nima Khademi","year":"2015","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_13_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-33507-0_21"},{"key":"e_1_2_13_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766997"},{"key":"e_1_2_13_32_3","unstructured":"url:https:\/\/doi.org\/10.1145\/27669973 7."},{"key":"e_1_2_13_33_2","unstructured":"Kalojanov JavorandThurston Kimball.Robust Average Networks for Monte Carlo Denoising.2025. arXiv: 2310.04080 [cs.GR]. url:https:\/\/arxiv.org\/abs\/2310.040804."},{"key":"e_1_2_13_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530158"},{"key":"e_1_2_13_34_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3528223.35301583 7."},{"key":"e_1_2_13_35_2","article-title":"Gradient-Domain Metropolis Light Transport","volume":"32","author":"Lehtinen Jaakko","year":"2013","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_13_36_2","unstructured":"Lumberyard Amazon.Amazon Lumberyard Bistro Open Research Content Archive (ORCA).http:\/\/developer.nvidia.com\/orca\/amazon-lumberyard-bistro. July2017. url:http:\/\/developer.nvidia.com\/orca\/amazon-lumberyard-bistro6."},{"key":"e_1_2_13_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459831"},{"key":"e_1_2_13_37_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3450626.34598316."},{"key":"e_1_2_13_38_2","first-page":"4","volume-title":"Computer Graphics Forum","author":"Munkberg Jacob","year":"2020"},{"key":"e_1_2_13_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980256"},{"key":"e_1_2_13_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417804"},{"key":"e_1_2_13_40_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3414685.34178042."},{"key":"e_1_2_13_41_2","doi-asserted-by":"publisher","DOI":"10.2312\/sr.20201133"},{"key":"e_1_2_13_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592139"},{"key":"e_1_2_13_43_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14378"},{"key":"e_1_2_13_43_3","unstructured":"eprint:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14378."},{"key":"e_1_2_13_43_4","unstructured":"url:https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/cgf.143787."},{"key":"e_1_2_13_44_2","unstructured":"Ronneberger Olaf Fischer Philipp andBrox Thomas.U-Net: Convolutional Networks for Biomedical Image Segmentation.2015. arXiv: 1505.04597 [cs.CV]. url:https:\/\/arxiv.org\/abs\/1505.045975."},{"key":"e_1_2_13_45_2","first-page":"169:1","article-title":"Image-space Control Variates for Rendering","volume":"35","author":"Rousselle Fabrice","year":"2016","journal-title":"ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)"},{"key":"e_1_2_13_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3388538"},{"key":"e_1_2_13_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555450"},{"key":"e_1_2_13_48_2","article-title":"Monte Carlo Geometry Processing: A Grid-Free Approach to PDE-Based Methods on Volumetric Domains","volume":"39","author":"Sawhney Rohan","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_13_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530095"},{"key":"e_1_2_13_49_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3528223.35300952."},{"key":"e_1_2_13_50_2","doi-asserted-by":"crossref","unstructured":"Schied Christoph Kaplanyan Anton Wyman Chris et al. \u201cSpatiotemporal variance-guided filtering: real-time reconstruction for path-traced global illumination\u201d.Proceedings of High Performance Graphics.2017 1\u2013127.","DOI":"10.1145\/3105762.3105770"},{"key":"e_1_2_13_51_2","doi-asserted-by":"crossref","unstructured":"Sawhney Rohan Lin Daqi Kettunen Markus et al. \u201cDecorrelating ReSTIR Samplers via MCMC Mutations\u201d.ACM Transactions on Graphics (ToG)(Jan.2024) to appear. doi:10.1145\/3629166. eprint: 2211.00166 7.","DOI":"10.1145\/3629166"},{"key":"e_1_2_13_52_2","unstructured":"Van de Woestijne Joran Frederickx Roald Billen Niels andDutr\u00e9 Philip. \u201cTemporal Coherence for Metropolis Light Transport.\u201dEGSR (EI&I).2017 55\u2013637."},{"key":"e_1_2_13_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201388"},{"key":"e_1_2_13_54_2","unstructured":"Wang Xintao Chan Kelvin CK Yu Ke et al. \u201cEDVR: Video Restoration with Enhanced Deformable Convolutional Networks\u201d.The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).20194."},{"key":"e_1_2_13_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392436"},{"key":"e_1_2_13_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555388"},{"key":"e_1_2_13_56_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3550469.35553887."},{"key":"e_1_2_13_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3687949"},{"key":"e_1_2_13_57_3","unstructured":"url:https:\/\/doi.org\/10.1145\/36879497."},{"key":"e_1_2_13_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3730400"},{"key":"e_1_2_13_58_3","unstructured":"url:https:\/\/doi.org\/10.1145\/37304004."},{"key":"e_1_2_13_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618211"},{"key":"e_1_2_13_59_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3610548.36182114."},{"key":"e_1_2_13_60_2","article-title":"Residual path integrals for re-rendering","volume":"43","author":"Xu Bing","year":"2024","journal-title":"Computer Graphics Forum (Proceedings of EGSR)"},{"key":"e_1_2_13_61_2","first-page":"224:1","article-title":"Adversarial Monte Carlo Denoising with Conditioned Auxiliary Feature","volume":"38","author":"Xu Bing","year":"2019","journal-title":"ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH Asia 2019)"},{"key":"e_1_2_13_62_2","first-page":"273","article-title":"Monte Carlo denoising via auxiliary feature guided self-attention","volume":"40","author":"Yu Jiaqi","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_13_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_12"},{"key":"e_1_2_13_64_2","first-page":"2","volume-title":"Computer graphics forum","author":"Zwicker Matthias","year":"2015"},{"key":"e_1_2_13_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658210"},{"key":"e_1_2_13_65_3","unstructured":"url:https:\/\/doi.org\/10.1145\/36582107."},{"key":"e_1_2_13_66_2","first-page":"2","volume-title":"Computer Graphics Forum","author":"Zeng Zheng","year":"2021"},{"key":"e_1_2_13_67_2","article-title":"Path-space Motion Estimation and Decomposition for Robust Animation Filtering","volume":"34","author":"Zimmer Henning","year":"2015","journal-title":"Computer Graphics Forum (Proceedings of EGSR)"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70358","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70358","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T10:20:22Z","timestamp":1779272422000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70358"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":87,"alternative-id":["10.1111\/cgf.70358"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70358","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"2026-05-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70358"}}