{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T02:40:12Z","timestamp":1774924812395,"version":"3.50.1"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T00:00:00Z","timestamp":1636502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["1703957 and 1764078"],"award-info":[{"award-number":["1703957 and 1764078"]}]},{"name":"Google Ph.D. Fellowships"},{"name":"UC San Diego Center for Visual Computing"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,2,28]]},"abstract":"<jats:p>Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful variance-reduction techniques is path guiding, which can learn better distributions for importance sampling to reduce pixel noise. However, previous methods require a large number of path samples to achieve reliable path guiding. We present a novel neural path guiding approach that can reconstruct high-quality sampling distributions for path guiding from a sparse set of samples, using an offline trained neural network. We leverage photons traced from light sources as the primary input for sampling density reconstruction, which is effective for challenging scenes with strong global illumination. To fully make use of our deep neural network, we partition the scene space into an adaptive hierarchical grid, in which we apply our network to reconstruct high-quality sampling distributions for any local region in the scene. This allows for effective path guiding for arbitrary path bounce at any location in path tracing. We demonstrate that our photon-driven neural path guiding approach can generalize to diverse testing scenes, often achieving better rendering results than previous path guiding approaches and opening up interesting future directions.<\/jats:p>","DOI":"10.1145\/3476828","type":"journal-article","created":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T20:09:13Z","timestamp":1636574953000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Photon-Driven Neural Reconstruction for Path Guiding"],"prefix":"10.1145","volume":"41","author":[{"given":"Shilin","family":"Zhu","sequence":"first","affiliation":[{"name":"University of California San Diego, CA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Adobe Research, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiancheng","family":"Sun","sequence":"additional","affiliation":[{"name":"University of California San Diego, CA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandr","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"University of California San Diego, CA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Meyer","sequence":"additional","affiliation":[{"name":"Pixar Animation Studios, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrik Wann","family":"Jensen","sequence":"additional","affiliation":[{"name":"University of California San Diego and Luxion, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Su","sequence":"additional","affiliation":[{"name":"University of California San Diego, CA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi","family":"Ramamoorthi","sequence":"additional","affiliation":[{"name":"University of California San Diego, CA, U.S.A"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,11,10]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13858"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073708"},{"key":"e_1_2_2_3_1","volume-title":"Retrieved","author":"Bitterli Benedikt","year":"2016","unstructured":"Benedikt Bitterli . 2016 . Rendering Resources . Retrieved July 31, 2021 from https:\/\/benedikt-bitterli.me\/resources\/. Benedikt Bitterli. 2016. Rendering Resources. Retrieved July 31, 2021 from https:\/\/benedikt-bitterli.me\/resources\/."},{"key":"e_1_2_2_4_1","unstructured":"Blend Swap Models. 2020. Retrieved from https:\/\/www.blendswap.com\/.  Blend Swap Models. 2020. Retrieved from https:\/\/www.blendswap.com\/."},{"key":"e_1_2_2_5_1","volume-title":"Retrieved","author":"Trader CG","year":"2020","unstructured":"CG Trader . 2020 . CG Trader . Retrieved July 31, 2021 from http:\/\/www.cgtrader.com. CG Trader. 2020. CG Trader. Retrieved July 31, 2021 from http:\/\/www.cgtrader.com."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073601"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14051"},{"key":"e_1_2_2_10_1","unstructured":"Evermotion 3D models. 2020. Retrieved from https:\/\/evermotion.org\/.  Evermotion 3D models. 2020. Retrieved from https:\/\/evermotion.org\/."},{"key":"e_1_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Marc-Andr\u00e9 Gardner Kalyan Sunkavalli Ersin Yumer Xiaohui Shen Emiliano Gambaretto Christian Gagn\u00e9 and Jean-Fran\u00e7ois Lalonde. 2017. Learning to predict indoor illumination from a single image. arXiv:1704.00090.  Marc-Andr\u00e9 Gardner Kalyan Sunkavalli Ersin Yumer Xiaohui Shen Emiliano Gambaretto Christian Gagn\u00e9 and Jean-Fran\u00e7ois Lalonde. 2017. Learning to predict indoor illumination from a single image. arXiv:1704.00090.","DOI":"10.1145\/3130800.3130891"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237200"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.2312\/sre.20181174"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1661412.1618487"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1457515.1409083"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3071773.3071781"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368313"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_2_2_19_1","volume-title":"Retrieved","author":"Jakob Wenzel","year":"2010","unstructured":"Wenzel Jakob . 2010 . Mitsuba Renderer . Retrieved July 31, 2021 from http:\/\/www.mitsuba-renderer.org. Wenzel Jakob. 2010. Mitsuba Renderer. Retrieved July 31, 2021 from http:\/\/www.mitsuba-renderer.org."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-9430-0_31"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/275458.275461"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2020.09.007"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_2_24_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A method for stochastic optimization. arXiv:1412.6980. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1966394.1966404"},{"key":"e_1_2_2_26_1","volume-title":"Willems","author":"Lafortune Eric P.","year":"1993","unstructured":"Eric P. Lafortune and Yves D . Willems . 1993 . Bi-directional path tracing. In Compugraphics\u2019 93. 145\u2013153. Eric P. Lafortune and Yves D. Willems. 1993. Bi-directional path tracing. In Compugraphics\u201993. 145\u2013153."},{"key":"e_1_2_2_27_1","volume-title":"Proceedings of the 18th International Conference on Artificial Intelligence and Statistics. 562\u2013570","author":"Lee Chen-Yu","year":"2015","unstructured":"Chen-Yu Lee , Saining Xie , Patrick Gallagher , Zhengyou Zhang , and Zhuowen Tu . 2015 . Deeply-supervised nets . In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics. 562\u2013570 . Chen-Yu Lee, Saining Xie, Patrick Gallagher, Zhengyou Zhang, and Zhuowen Tu. 2015. Deeply-supervised nets. In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics. 562\u2013570."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3305366.3328091"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13227"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341156"},{"key":"e_1_2_2_32_1","volume-title":"Retrieved","author":"CV.","year":"2021","unstructured":"Open CV. 2021 . Image Pyramids . Retrieved July 31, 2021 from https:\/\/docs.opencv.org. OpenCV. 2021. Image Pyramids. Retrieved July 31, 2021 from https:\/\/docs.opencv.org."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778803"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/647652.732117"},{"key":"e_1_2_2_36_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652\u2013660","author":"Qi Charles R.","unstructured":"Charles R. Qi , Hao Su , Kaichun Mo , and Leonidas J. Guibas . 2017. PointNet: Deep learning on point sets for 3D classification and segmentation . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652\u2013660 . Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652\u2013660."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392441"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275030"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392421"},{"key":"e_1_2_2_41_1","volume-title":"Greenberg","author":"Shirley Peter","year":"1995","unstructured":"Peter Shirley , Bretton Wade , Philip M. Hubbard , David Zareski , Bruce Walter , and Donald P . Greenberg . 1995 . Global illumination via density-estimation. In Rendering Techniques, 95. Eurographics Book Series. Springer , 219\u2013230. Peter Shirley, Bretton Wade, Philip M. Hubbard, David Zareski, Bruce Walter, and Donald P. Greenberg. 1995. Global illumination via density-estimation. In Rendering Techniques, 95. Eurographics Book Series. Springer, 219\u2013230."},{"key":"e_1_2_2_42_1","unstructured":"3D Models Plugins Textures and More at Turbo Squid. 2020. Retrieved from https:\/\/www.turbosquid.com\/.  3D Models Plugins Textures and More at Turbo Squid. 2020. Retrieved from https:\/\/www.turbosquid.com\/."},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/927297"},{"key":"e_1_2_2_44_1","volume-title":"Photorealistic Rendering Techniques","author":"Veach Eric","unstructured":"Eric Veach and Leonidas Guibas . 1995a. Bidirectional estimators for light transport . In Photorealistic Rendering Techniques . Springer , 145\u2013167. Eric Veach and Leonidas Guibas. 1995a. Bidirectional estimators for light transport. In Photorealistic Rendering Techniques. Springer, 145\u2013167."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218498"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258775"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201388"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3305366.3328091"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601203"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201313"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00753"},{"key":"e_1_2_2_53_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 4471\u20134480","author":"Yu Jiahui","unstructured":"Jiahui Yu , Zhe Lin , Jimei Yang , Xiaohui Shen , Xin Lu , and Thomas S. Huang . 2019. Free-form image inpainting with gated convolution . In Proceedings of the IEEE International Conference on Computer Vision. 4471\u20134480 . Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S. Huang. 2019. Free-form image inpainting with gated convolution. In Proceedings of the IEEE International Conference on Computer Vision. 4471\u20134480."},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14052"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459810"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3476828","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3476828","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3476828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:20Z","timestamp":1750268960000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3476828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,10]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2,28]]}},"alternative-id":["10.1145\/3476828"],"URL":"https:\/\/doi.org\/10.1145\/3476828","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,10]]},"assertion":[{"value":"2020-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}