{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T02:15:50Z","timestamp":1774059350298,"version":"3.50.1"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T00:00:00Z","timestamp":1580256000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"MSIT\/NRF","award":["2019R1A2C3002833 and NRF-2017M3C4A7066317"],"award-info":[{"award-number":["2019R1A2C3002833 and NRF-2017M3C4A7066317"]}]},{"name":"National Key R8D Program of China","award":["2017YFB1002605"],"award-info":[{"award-number":["2017YFB1002605"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61872319"],"award-info":[{"award-number":["61872319"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Provincial NSFC","award":["LR18F020002"],"award-info":[{"award-number":["LR18F020002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2020,2,29]]},"abstract":"<jats:p>Serious noise affects the rendering of global illumination using Monte Carlo (MC) path tracing when insufficient samples are used. The two common solutions to this problem are filtering noisy inputs to generate smooth but biased results and sampling the MC integrand with a carefully crafted probability distribution function (PDF) to produce unbiased results. Both solutions benefit from an efficient incident radiance field sampling and reconstruction algorithm. This study proposes a method for training quality and reconstruction networks (Q- and R-networks, respectively) with a massive offline dataset for the adaptive sampling and reconstruction of first-bounce incident radiance fields. The convolutional neural network (CNN)-based R-network reconstructs the incident radiance field in a 4D space, whereas the deep reinforcement learning (DRL)-based Q-network predicts and guides the adaptive sampling process. The approach is verified by comparing it with state-of-the-art unbiased path guiding methods and filtering methods. Results demonstrate improvements for unbiased path guiding and competitive performance in biased applications, including filtering and irradiance caching.<\/jats:p>","DOI":"10.1145\/3368313","type":"journal-article","created":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T12:38:08Z","timestamp":1580301488000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Adaptive Incident Radiance Field Sampling and Reconstruction Using Deep Reinforcement Learning"],"prefix":"10.1145","volume":"39","author":[{"given":"Yuchi","family":"Huo","sequence":"first","affiliation":[{"name":"KAIST and State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruzahng","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hualin","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Eui","family":"Yoon","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,1,29]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Matthieu Devin et al","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi , Ashish Agarwal , Paul Barham , Eugene Brevdo , Zhifeng Chen , Craig Citro , Greg S. Corrado , Andy Davis , Jeffrey Dean , Matthieu Devin et al . 2016 . Tensorflow : Large-scale machine learning on heterogeneous distributed systems. Retrieved from arXiv preprint arXiv:1603.04467 (2016). Mart\u00edn Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin et al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. Retrieved from arXiv preprint arXiv:1603.04467 (2016)."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073708"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12954"},{"key":"e_1_2_2_4_1","volume-title":"Joy","author":"Budge B. C.","year":"2008","unstructured":"B. C. Budge , John C. Anderson , and Kenneth I . Joy . 2008 . Caustic forecasting: Unbiased estimation of caustic lighting for global illumination. In Proceedings of the Computer Graphics Forum, Vol. 27 . Wiley Online Library , 1963--1970. B. C. Budge, John C. Anderson, and Kenneth I. Joy. 2008. Caustic forecasting: Unbiased estimation of caustic lighting for global illumination. In Proceedings of the Computer Graphics Forum, Vol. 27. Wiley Online Library, 1963--1970."},{"key":"e_1_2_2_5_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 Trans. Graph. 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 Trans. Graph. 36, 4 (2017), 98.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3084363.3085032"},{"key":"e_1_2_2_7_1","volume-title":"Learning light transport the reinforced way. Retrieved from arXiv preprint arXiv:1701.07403","author":"Dahm Ken","year":"2017","unstructured":"Ken Dahm and Alexander Keller . 2017b. Learning light transport the reinforced way. Retrieved from arXiv preprint arXiv:1701.07403 ( 2017 ). Ken Dahm and Alexander Keller. 2017b. Learning light transport the reinforced way. Retrieved from arXiv preprint arXiv:1701.07403 (2017)."},{"key":"e_1_2_2_8_1","volume-title":"Machine learning and integral equations. Retrieved from arXiv preprint arXiv:1712.06115","author":"Dahm Ken","year":"2017","unstructured":"Ken Dahm and Alexander Keller . 2017c. Machine learning and integral equations. Retrieved from arXiv preprint arXiv:1712.06115 ( 2017 ). Ken Dahm and Alexander Keller. 2017c. Machine learning and integral equations. Retrieved from arXiv preprint arXiv:1712.06115 (2017)."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024214"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1944846.1944849"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531399"},{"key":"e_1_2_2_12_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5515--5524","author":"Flynn John","year":"2016","unstructured":"John Flynn , Ivan Neulander , James Philbin , and Noah Snavely . 2016 . Deepstereo: Learning to predict new views from the world\u2019s imagery . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5515--5524 . John Flynn, Ivan Neulander, James Philbin, and Noah Snavely. 2016. Deepstereo: Learning to predict new views from the world\u2019s imagery. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5515--5524."},{"key":"e_1_2_2_13_1","volume-title":"Proceedings of the 13th 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 13th 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 13th International Conference on Artificial Intelligence and Statistics. 249--256."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360632"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12950"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2820926.2820955"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818120"},{"key":"e_1_2_2_19_1","unstructured":"Wenzel Jakob. 2010. Mitsuba renderer. Retrieved from http:\/\/www.mitsuba-renderer.org.  Wenzel Jakob. 2010. Mitsuba renderer. Retrieved from http:\/\/www.mitsuba-renderer.org."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185554"},{"key":"e_1_2_2_21_1","volume-title":"Rendering Techniques \u201995","author":"Jensen Henrik Wann","unstructured":"Henrik Wann Jensen . 1995. Importance driven path tracing using the photon map . In Rendering Techniques \u201995 . Springer , 326--335. Henrik Wann Jensen. 1995. Importance driven path tracing using the photon map. In Rendering Techniques \u201995. Springer, 326--335."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766977"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130880"},{"key":"e_1_2_2_25_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. Retrieved from arXiv preprint arXiv:1412.6980 (2014). Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. Retrieved from arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_26_1","volume-title":"Optimal Control Theory: An Introduction","author":"Kirk Donald E.","unstructured":"Donald E. Kirk . 2012. Optimal Control Theory: An Introduction . Courier Corporation . Donald E. Kirk. 2012. Optimal Control Theory: An Introduction. Courier Corporation."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964950"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185547"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461947"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601113"},{"key":"e_1_2_2_31_1","volume-title":"Georg Ostrovski et al","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Andrei A. Rusu , Joel Veness , Marc G. Bellemare , Alex Graves , Martin Riedmiller , Andreas K. Fidjeland , Georg Ostrovski et al . 2015 . Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925936"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13227"},{"key":"e_1_2_2_34_1","volume-title":"Neural importance sampling. CoRR abs\/1808.03856","author":"M\u00fcller Thomas","year":"2018","unstructured":"Thomas M\u00fcller , Brian McWilliams , Fabrice Rousselle , Markus Gross , and Jan Nov\u00e1k . 2018. Neural importance sampling. CoRR abs\/1808.03856 ( 2018 ). Retrieved from http:\/\/arxiv.org\/abs\/1808.03856. Thomas M\u00fcller, Brian McWilliams, Fabrice Rousselle, Markus Gross, and Jan Nov\u00e1k. 2018. Neural importance sampling. CoRR abs\/1808.03856 (2018). Retrieved from http:\/\/arxiv.org\/abs\/1808.03856."},{"key":"e_1_2_2_35_1","volume-title":"Papadimitriou and Kenneth Steiglitz","author":"Christos","year":"1998","unstructured":"Christos H. Papadimitriou and Kenneth Steiglitz . 1998 . Combinatorial Optimization : Algorithms and Complexity. Courier Corporation . Christos H. Papadimitriou and Kenneth Steiglitz. 1998. Combinatorial Optimization: Algorithms and Complexity. Courier Corporation."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366214"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12219"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3105762.3105770"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3233301"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2167076.2167083"},{"key":"e_1_2_2_42_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot et al.","author":"Silver David","year":"2016","unstructured":"David Silver , Aja Huang , Chris J. Maddison , Arthur Guez , Laurent Sifre , George Van Den Driessche , Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot et al. 2016 . Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484--489. David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot et al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484--489."},{"key":"e_1_2_2_43_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201916)","volume":"16","author":"Hasselt Hado Van","year":"2016","unstructured":"Hado Van Hasselt , Arthur Guez , and David Silver . 2016 . Deep reinforcement learning with double Q-learning . In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201916) , Vol. 16 . 2094--2100. Hado Van Hasselt, Arthur Guez, and David Silver. 2016. Deep reinforcement learning with double Q-learning. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201916), Vol. 16. 2094--2100."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201340"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201388"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601203"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925912"},{"key":"e_1_2_2_49_1","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems. 341--349","author":"Xie Junyuan","year":"2012","unstructured":"Junyuan Xie , Linli Xu , and Enhong Chen . 2012 . Image denoising and inpainting with deep neural networks . In Proceedings of the Conference on Advances in Neural Information Processing Systems. 341--349 . Junyuan Xie, Linli Xu, and Enhong Chen. 2012. Image denoising and inpainting with deep neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 341--349."},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816814"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_2_2_52_1","volume-title":"Learning to importance sample in primary sample space. CoRR abs\/1808.07840","author":"Zheng Quan","year":"2018","unstructured":"Quan Zheng and Matthias Zwicker . 2018. Learning to importance sample in primary sample space. CoRR abs\/1808.07840 ( 2018 ). arxiv:1808.07840 --&gt;Retrieved from http:\/\/arxiv.org\/abs\/1808.07840. Quan Zheng and Matthias Zwicker. 2018. Learning to importance sample in primary sample space. CoRR abs\/1808.07840 (2018). arxiv:1808.07840 --&gt;Retrieved from http:\/\/arxiv.org\/abs\/1808.07840."},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12592"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368313","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3368313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:25Z","timestamp":1750197685000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,29]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,2,29]]}},"alternative-id":["10.1145\/3368313"],"URL":"https:\/\/doi.org\/10.1145\/3368313","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,29]]},"assertion":[{"value":"2018-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-01-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}