{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T07:59:40Z","timestamp":1767167980127,"version":"build-2238731810"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,8,31]]},"abstract":"<jats:p>Image-space auxiliary features such as surface normal have significantly contributed to the recent success of Monte Carlo (MC) reconstruction networks. However, path-space features, another essential piece of light propagation, have not yet been sufficiently explored. Due to the curse of dimensionality, information flow between a regression loss and high-dimensional path-space features is sparse, leading to difficult training and inefficient usage of path-space features in a typical reconstruction framework. This paper introduces a contrastive manifold learning framework to utilize path-space features effectively. The proposed framework employs weakly-supervised learning that converts reference pixel colors to dense pseudo labels for light paths. A convolutional path-embedding network then induces a low-dimensional manifold of paths by iteratively clustering intra-class embeddings, while discriminating inter-class embeddings using gradient descent. The proposed framework facilitates path-space exploration of reconstruction networks by extracting low-dimensional yet meaningful embeddings within the features. We apply our framework to the recent image- and sample-space models and demonstrate considerable improvements, especially on the sample space. The source code is available at https:\/\/github.com\/Mephisto405\/WCMC.<\/jats:p>","DOI":"10.1145\/3450626.3459876","type":"journal-article","created":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T20:04:26Z","timestamp":1626725066000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Weakly-supervised contrastive learning in path manifold for Monte Carlo image reconstruction"],"prefix":"10.1145","volume":"40","author":[{"given":"In-Young","family":"Cho","sequence":"first","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchi","family":"Huo","sequence":"additional","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Eui","family":"Yoon","sequence":"additional","affiliation":[{"name":"KAIST, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi and 2016 . Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016). Mart\u00edn Abadi and et al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13548"},{"key":"e_1_2_2_3_1","volume-title":"Computer Graphics Forum","author":"Bako Steve","unstructured":"Steve Bako , Mark Meyer , Tony DeRose , and Pradeep Sen . 2019. Offline deep importance sampling for Monte Carlo path tracing . In Computer Graphics Forum , Vol. 38 . Wiley Online Library , 527--542. Steve Bako, Mark Meyer, Tony DeRose, and Pradeep Sen. 2019. Offline deep importance sampling for Monte Carlo path tracing. In Computer Graphics Forum, Vol. 38. Wiley Online Library, 527--542."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073708"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13540"},{"key":"e_1_2_2_6_1","unstructured":"Benedikt Bitterli. 2016. Rendering resources. https:\/\/benedikt-bitterli.me\/resources\/.  Benedikt Bitterli. 2016. Rendering resources. https:\/\/benedikt-bitterli.me\/resources\/."},{"key":"e_1_2_2_7_1","volume-title":"Random forests. Machine learning 45, 1","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman . 2001. Random forests. Machine learning 45, 1 ( 2001 ), 5--32. Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5--32."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1137\/040616024"},{"key":"e_1_2_2_9_1","first-page":"98","article-title":"Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder","volume":"36","author":"Alla Chaitanya Chakravarty R","year":"2017","unstructured":"Chakravarty R Alla Chaitanya , Anton S Kaplanyan , Christoph Schied , Marco Salvi , Aaron Lefohn , Derek Nowrouzezahrai , and Timo Aila . 2017 . Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder . ACM Transactions on Graphics (TOG) 36 , 4 (2017), 98 . Chakravarty R Alla Chaitanya, Anton S Kaplanyan, Christoph Schied, Marco Salvi, Aaron Lefohn, Derek Nowrouzezahrai, and Timo Aila. 2017. Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder. ACM Transactions on Graphics (TOG) 36, 4 (2017), 98.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Shixing Chen Caojin Zhang Ming Dong Jialiang Le and Mike Rao. 2017. Using Ranking-CNN for Age Estimation. In CVPR.  Shixing Chen Caojin Zhang Ming Dong Jialiang Le and Mike Rao. 2017. Using Ranking-CNN for Age Estimation. In CVPR.","DOI":"10.1109\/CVPR.2017.86"},{"key":"e_1_2_2_11_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen , Simon Kornblith , Mohammad Norouzi , and Geoffrey Hinton . 2020 . A simple framework for contrastive learning of visual representations . In International conference on machine learning. PMLR, 1597--1607 . Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2532708"},{"key":"e_1_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Jiankang Deng Jia Guo Niannan Xue and Stefanos Zafeiriou. 2019. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In CVPR.  Jiankang Deng Jia Guo Niannan Xue and Stefanos Zafeiriou. 2019. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In CVPR.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_2_2_14_1","volume-title":"Flash photography enhancement via intrinsic relighting. ACM transactions on graphics (TOG) 23, 3","author":"Eisemann Elmar","year":"2004","unstructured":"Elmar Eisemann and Fr\u00e9do Durand . 2004. Flash photography enhancement via intrinsic relighting. ACM transactions on graphics (TOG) 23, 3 ( 2004 ), 673--678. Elmar Eisemann and Fr\u00e9do Durand. 2004. Flash photography enhancement via intrinsic relighting. ACM transactions on graphics (TOG) 23, 3 (2004), 673--678."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982399"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322954"},{"key":"e_1_2_2_17_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. 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. 249--256 . 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. 249--256."},{"key":"e_1_2_2_18_1","unstructured":"Raia Hadsell Sumit Chopra and Yann LeCun. 2006. Dimensionality Reduction by Learning an Invariant Mapping. In CVPR.  Raia Hadsell Sumit Chopra and Yann LeCun. 2006. Dimensionality Reduction by Learning an Invariant Mapping. In CVPR."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2858834.2858844"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/2858834.2858842"},{"key":"e_1_2_2_21_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In CVPR."},{"key":"e_1_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Paul S Heckbert. 1990. Adaptive radiosity textures for bidirectional ray tracing. In Computer graphics and interactive techniques.  Paul S Heckbert. 1990. Adaptive radiosity textures for bidirectional ray tracing. In Computer graphics and interactive techniques.","DOI":"10.1145\/97879.97895"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368313"},{"key":"e_1_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Woobin Im Sungeun Hong Sung-Eui Yoon and Hyun S Yang. 2018. Scale-Varying Triplet Ranking with Classification Loss for Facial Age Estimation. In ACCV. 247--259.  Woobin Im Sungeun Hong Sung-Eui Yoon and Hyun S Yang. 2018. Scale-Varying Triplet Ranking with Classification Loss for Facial Age Estimation. In ACCV. 247--259.","DOI":"10.1007\/978-3-030-20873-8_16"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185554"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766977"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601108"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11091066"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323038"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766997"},{"key":"e_1_2_2_33_1","volume-title":"Supervised contrastive learning. arXiv preprint arXiv:2004.11362","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla , Piotr Teterwak , Chen Wang , Aaron Sarna , Yonglong Tian , Phillip Isola , Aaron Maschinot , Ce Liu , and Dilip Krishnan . 2020. Supervised contrastive learning. arXiv preprint arXiv:2004.11362 ( 2020 ). Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. arXiv preprint arXiv:2004.11362 (2020)."},{"key":"e_1_2_2_34_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). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_35_1","volume-title":"Path-based Monte Carlo Denoising Using a Three-Scale Neural Network. Computer Graphics Forum","author":"Lin Weiheng","year":"2021","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. Computer Graphics Forum ( 2021 ). Weiheng Lin, Beibei Wang, Jian Yang, Lu Wang, and Ling-Qi Yan. 2021. Path-based Monte Carlo Denoising Using a Three-Scale Neural Network. Computer Graphics Forum (2021)."},{"key":"e_1_2_2_36_1","first-page":"2579","article-title":"Visualizing data using t-SNE","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton . 2008 . Visualizing data using t-SNE . Journal of machine learning research 9 , Nov (2008), 2579 -- 2605 . Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, Nov (2008), 2579--2605.","journal-title":"Journal of machine learning research 9"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2641762"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12004"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925936"},{"key":"e_1_2_2_40_1","volume-title":"Computer Graphics Forum","author":"M\u00fcller Thomas","unstructured":"Thomas M\u00fcller , Markus Gross , and Jan Nov\u00e1k . 2017. Practical path guiding for efficient light-transport simulation . In Computer Graphics Forum , Vol. 36 . Wiley Online Library , 91--100. Thomas M\u00fcller, Markus Gross, and Jan Nov\u00e1k. 2017. Practical path guiding for efficient light-transport simulation. In Computer Graphics Forum, Vol. 36. Wiley Online Library, 91--100."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341156"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14049"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2447976.2447997"},{"key":"e_1_2_2_44_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566575"},{"key":"e_1_2_2_46_1","volume-title":"Computer Graphics Forum","author":"Rousselle Fabrice","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. 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_2_47_1","volume-title":"Learning representations by back-propagating errors. nature 323, 6088","author":"Rumelhart David E","year":"1986","unstructured":"David E Rumelhart , Geoffrey E Hinton , and Ronald J Williams . 1986. Learning representations by back-propagating errors. nature 323, 6088 ( 1986 ), 533--536. David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature 323, 6088 (1986), 533--536."},{"key":"e_1_2_2_48_1","volume-title":"Annual Conference on Neural Information Processing Systems 2014","author":"Sun Yi","year":"2014","unstructured":"Yi Sun , Yuheng Chen , Xiaogang Wang , and Xiaoou Tang . 2014 . Deep Learning Face Representation by Joint Identification-Verification . In Annual Conference on Neural Information Processing Systems 2014 . Montreal, Quebec, Canada , 1988--1996. Yi Sun, Yuheng Chen, Xiaogang Wang, and Xiaoou Tang. 2014. Deep Learning Face Representation by Joint Identification-Verification. In Annual Conference on Neural Information Processing Systems 2014. Montreal, Quebec, Canada, 1988--1996."},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01382"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3378678.3391882"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201388"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601203"},{"key":"e_1_2_2_53_1","volume-title":"Deep Metric Learning with Angular Loss. In IEEE International Conference on Computer Vision, ICCV","author":"Wang Jian","year":"2017","unstructured":"Jian Wang , Feng Zhou , Shilei Wen , Xiao Liu , and Yuanqing Lin . 2017 . Deep Metric Learning with Angular Loss. In IEEE International Conference on Computer Vision, ICCV 2017. IEEE Computer Society, Venice, Italy, 2612--2620. Jian Wang, Feng Zhou, Shilei Wen, Xiao Liu, and Yuanqing Lin. 2017. Deep Metric Learning with Angular Loss. In IEEE International Conference on Computer Vision, ICCV 2017. IEEE Computer Society, Venice, Italy, 2612--2620."},{"key":"e_1_2_2_54_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. 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_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"e_1_2_2_56_1","unstructured":"Zhirong Wu Yuanjun Xiong Stella X Yu and Dahua Lin. 2018. Unsupervised feature learning via non-parametric instance discrimination. In CVPR.  Zhirong Wu Yuanjun Xiong Stella X Yu and Dahua Lin. 2018. Unsupervised feature learning via non-parametric instance discrimination. In CVPR."},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356547"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392408"},{"key":"e_1_2_2_59_1","volume-title":"Computer Graphics Forum","author":"Zheng Quan","unstructured":"Quan Zheng and Matthias Zwicker . 2019. Learning to importance sample in primary sample space . In Computer Graphics Forum , Vol. 38 . Wiley Online Library , 169--179. Quan Zheng and Matthias Zwicker. 2019. Learning to importance sample in primary sample space. In Computer Graphics Forum, Vol. 38. Wiley Online Library, 169--179."},{"key":"e_1_2_2_60_1","volume-title":"A brief introduction to weakly supervised learning. National science review 5, 1","author":"Zhou Zhi-Hua","year":"2018","unstructured":"Zhi-Hua Zhou . 2018. A brief introduction to weakly supervised learning. National science review 5, 1 ( 2018 ), 44--53. Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review 5, 1 (2018), 44--53."},{"key":"e_1_2_2_61_1","volume-title":"Computer Graphics Forum","author":"Zimmer Henning","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 . In Computer Graphics Forum , Vol. 34 . Wiley Online Library , 131--142. 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. In Computer Graphics Forum, Vol. 34. Wiley Online Library, 131--142."},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201307"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450626.3459876","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3450626.3459876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:17:21Z","timestamp":1750177041000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450626.3459876"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,19]]},"references-count":61,"aliases":["10.1145\/3476576.3476581"],"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,8,31]]}},"alternative-id":["10.1145\/3450626.3459876"],"URL":"https:\/\/doi.org\/10.1145\/3450626.3459876","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,19]]},"assertion":[{"value":"2021-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}