{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:24:40Z","timestamp":1761582280080,"version":"3.41.0"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T00:00:00Z","timestamp":1683849600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2023-00208506"],"award-info":[{"award-number":["RS-2023-00208506"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Information Technology Research Center, Korea","award":["ITP-2023-2020-0-01460"],"award-info":[{"award-number":["ITP-2023-2020-0-01460"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2023,5,12]]},"abstract":"<jats:p>Auxiliary features such as geometric buffers (G-buffers) and path descriptors (P-buffers) have been shown to significantly improve Monte Carlo (MC) denoising. However, recent approaches implicitly learn to exploit auxiliary features for denoising, which could lead to insufficient utilization of each type of auxiliary features. To overcome such an issue, we propose a denoising framework that relies on an explicit pixel-wise guidance for utilizing auxiliary features. First, we train two denoisers, each trained by a different auxiliary feature (i.e., G-buffers or P-buffers). Then we design our ensembling network to obtain per-pixel ensembling weight maps, which represent pixel-wise guidance for which auxiliary feature should be dominant at reconstructing each individual pixel and use them to ensemble the two denoised results of our denosiers. We also propagate our pixel-wise guidance to the denoisers by jointly training the denoisers and the ensembling network, further guiding the denoisers to focus on regions where G-buffers or P-buffers are relatively important for denoising. Our result and show considerable improvement in denoising performance compared to the baseline denoising model using both G-buffers and P-buffers. The source code is available at https:\/\/github.com\/qbhan\/GuidanceMCDenoising.<\/jats:p>","DOI":"10.1145\/3585505","type":"journal-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T17:05:34Z","timestamp":1684256734000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1196-4548","authenticated-orcid":false,"given":"Kyu Beom","family":"Han","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3650-9058","authenticated-orcid":false,"given":"Olivia G.","family":"Odenthal","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8819-9716","authenticated-orcid":false,"given":"Woo Jae","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7123-1119","authenticated-orcid":false,"given":"Sung-Eui","family":"Yoon","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417847"},{"key":"e_1_2_1_2_1","volume-title":"Self-Supervised Post-Correction for Monte Carlo Denoising. In ACM SIGGRAPH 2022 Conference Proceedings. 1--8.","author":"Back Jonghee","year":"2022","unstructured":"Jonghee Back, Binh-Son Hua, Toshiya Hachisuka, and Bochang Moon. 2022. Self-Supervised Post-Correction for Monte Carlo Denoising. In ACM SIGGRAPH 2022 Conference Proceedings. 1--8."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073708"},{"volume-title":"Computer Graphics Forum","author":"Bauszat Pablo","key":"e_1_2_1_4_1","unstructured":"Pablo Bauszat, Martin Eisemann, Elmar Eisemann, and Marcus Magnor. 2015. General and robust error estimation and reconstruction for monte carlo rendering. In Computer Graphics Forum, Vol. 34. Wiley Online Library, 597--608."},{"key":"e_1_2_1_5_1","unstructured":"Benedikt Bitterli. 2016. Rendering resources. https:\/\/benedikt-bitterli.me\/resources\/."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073601"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459876"},{"key":"e_1_2_1_9_1","volume-title":"Jeppe Revall Frisvad, and Henrik Wann Jensen","author":"Firmino Arthur","year":"2022","unstructured":"Arthur Firmino, Jeppe Revall Frisvad, and Henrik Wann Jensen. 2022. Progressive Denoising of Monte Carlo Rendered Images. 41, 2 (2022), 1--11."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322954"},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555496"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766977"},{"key":"e_1_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"volume-title":"Computer Graphics Forum","author":"Lin Weiheng","key":"e_1_2_1_17_1","unstructured":"Weiheng Lin, Beibei Wang, Jian Yang, Lu Wang, and Ling-Qi Yan. 2021. Path-based Monte Carlo Denoising Using a Three-Scale Neural Network. In Computer Graphics Forum, Vol. 40. Wiley Online Library, 369--381."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/318009.318015"},{"key":"e_1_2_1_19_1","volume-title":"Neural denoising with layer embeddings. 39, 4","author":"Munkberg Jacob","year":"2020","unstructured":"Jacob Munkberg and Jon Hasselgren. 2020. Neural denoising with layer embeddings. 39, 4 (2020), 1--12."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2447976.2447997"},{"volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","key":"e_1_2_1_21_1","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 8024--8035."},{"key":"e_1_2_1_22_1","first-page":"1","article-title":"Real-Time Hair Filtering with Convolutional Neural Networks","volume":"5","author":"Currius R Ramon","year":"2022","unstructured":"R Ramon Currius, U Assarsson, and E Sintorn. 2022. Real-Time Hair Filtering with Convolutional Neural Networks. Neural Networks 5 (2022), 1.","journal-title":"Neural Networks"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024193"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366214"},{"volume-title":"Computer Graphics Forum","author":"Rousselle Fabrice","key":"e_1_2_1_25_1","unstructured":"Fabrice Rousselle, Marco Manzi, and Matthias Zwicker. 2013. Robust denoising using feature and color information. In Computer Graphics Forum, Vol. 32. Wiley Online Library, 121--130."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2167076.2167083"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201388"},{"key":"e_1_2_1_28_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600--612."},{"key":"e_1_2_1_29_1","volume-title":"Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks. arXiv preprint arXiv:2202.11782","author":"Whitaker Tim","year":"2022","unstructured":"Tim Whitaker and Darrell Whitley. 2022. Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks. arXiv preprint arXiv:2202.11782 (2022)."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356547"},{"key":"e_1_2_1_31_1","volume-title":"Image data augmentation for deep learning: A survey. arXiv preprint arXiv:2204.08610","author":"Yang Suorong","year":"2022","unstructured":"Suorong Yang, Weikang Xiao, Mengcheng Zhang, Suhan Guo, Jian Zhao, and Furao Shen. 2022. Image data augmentation for deep learning: A survey. arXiv preprint arXiv:2204.08610 (2022)."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00078"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480504"},{"key":"e_1_2_1_34_1","volume-title":"Automatic Feature Selection for Denoising Volumetric Renderings. 41, 4","author":"Zhang Xianyao","year":"2022","unstructured":"Xianyao Zhang, Melvin Ott, Marco Manzi, Markus Gross, and Marios Papas. 2022. Automatic Feature Selection for Denoising Volumetric Renderings. 41, 4 (2022), 63--77."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480510"},{"key":"e_1_2_1_36_1","volume-title":"Path-space motion estimation and decomposition for robust animation filtering. 34, 4","author":"Zimmer Henning","year":"2015","unstructured":"Henning Zimmer, Fabrice Rousselle, Wenzel Jakob, Oliver Wang, David Adler, Wojciech Jarosz, Olga Sorkine-Hornung, and Alexander Sorkine-Hornung. 2015. Path-space motion estimation and decomposition for robust animation filtering. 34, 4 (2015), 131--142."}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3585505","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3585505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:56Z","timestamp":1750178276000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3585505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,12]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,5,12]]}},"alternative-id":["10.1145\/3585505"],"URL":"https:\/\/doi.org\/10.1145\/3585505","relation":{},"ISSN":["2577-6193"],"issn-type":[{"type":"electronic","value":"2577-6193"}],"subject":[],"published":{"date-parts":[[2023,5,12]]},"assertion":[{"value":"2023-05-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}