{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T00:20:29Z","timestamp":1725582029803},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"6","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,12]]},"abstract":"We propose an adaptive sampling and reconstruction method for offline Monte Carlo rendering. Our method produces sampling maps constrained by a user-defined budget that minimize the expected future denoising error. Compared to other state-of-the-art methods, which produce the necessary training data on the fly by composing pre-rendered images, our method samples from analytic noise distributions instead. These distributions are compact and closely approximate the pixel value distributions stemming from Monte Carlo rendering. Our method can efficiently sample training data by leveraging only a few per-pixel statistics of the target distribution, which provides several benefits over the current state of the art. Most notably, our analytic distributions' modeling accuracy and sampling efficiency increase with sample count, essential for high-quality offline rendering. Although our distributions are approximate, our method supports joint end-to-end training of the sampling and denoising networks. Finally, we propose the addition of a global summary module to our architecture that accumulates valuable information from image regions outside of the network's receptive field. This information discourages sub-optimal decisions based on local information. Our evaluation against other state-of-the-art neural sampling methods demonstrates denoising quality and data efficiency improvements.<\/jats:p>","DOI":"10.1145\/3550454.3555515","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T21:19:07Z","timestamp":1669843147000},"page":"1-16","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep Adaptive Sampling and Reconstruction Using Analytic Distributions"],"prefix":"10.1145","volume":"41","author":[{"given":"Farnood","family":"Salehi","sequence":"first","affiliation":[{"name":"Disney Research | Studios, Switzerland"}]},{"given":"Marco","family":"Manzi","sequence":"additional","affiliation":[{"name":"Disney Research | Studios, Switzerland"}]},{"given":"Gerhard","family":"Roethlin","sequence":"additional","affiliation":[{"name":"Disney Research | Studios, Switzerland"}]},{"given":"Romann","family":"Weber","sequence":"additional","affiliation":[{"name":"Disney Research | Studios, Switzerland"}]},{"given":"Christopher","family":"Schroers","sequence":"additional","affiliation":[{"name":"Disney Research | Studios, Switzerland"}]},{"given":"Marios","family":"Papas","sequence":"additional","affiliation":[{"name":"Disney Research | Studios, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham et al. 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. http:\/\/tensorflow.org\/"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3406183"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073708"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882318"},{"key":"e_1_2_1_5_1","first-page":"2","article-title":"General and Robust Error Estimation and Reconstruction for Monte Carlo Rendering. Computer Graphics Forum (Proc","volume":"34","author":"Bauszat Pablo","year":"2015","unstructured":"Pablo Bauszat, Martin Eisemann, Elmar Eisemann, and Marcus Magnor. 2015. General and Robust Error Estimation and Reconstruction for Monte Carlo Rendering. Computer Graphics Forum (Proc. of Eurographics EG) 34, 2 (May 2015), 597--608. Eurographics 2015 paper.","journal-title":"of Eurographics EG)"},{"key":"e_1_2_1_6_1","volume-title":"Proc. Vision, Modeling and Visualization (VMV). Eurographics, 183--190","author":"Bauszat Pablo","year":"2011","unstructured":"Pablo Bauszat, Martin Eisemann, and Marcus Magnor. 2011. Adaptive Sampling for Geometry-aware Reconstruction Filters. In Proc. Vision, Modeling and Visualization (VMV). Eurographics, 183--190."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12954"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073601"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073320"},{"key":"e_1_2_1_10_1","unstructured":"Oskar Elek Manu M. Thomas and Angus Forbes. 2019. Learning Patterns in Sample Distributions for Monte Carlo Variance Reduction. arXiv:1906.00124 [cs.GR]"},{"key":"e_1_2_1_11_1","volume-title":"Garnett (Eds.)","volume":"31","author":"Figurnov Mikhail","year":"2018","unstructured":"Mikhail Figurnov, Shakir Mohamed, and Andriy Mnih. 2018. Implicit Reparameterization Gradients. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/92c8c96e4c37100777c7190b76d28233-Paper.pdf"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280888"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360632"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13919"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459793"},{"key":"e_1_2_1_16_1","unstructured":"Wenzel Jakob. 2010. Mitsuba renderer. http:\/\/www.mitsuba-renderer.org."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766977"},{"key":"e_1_2_1_18_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/122718.122735"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13473"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366213"},{"key":"e_1_2_1_22_1","article-title":"SURE-based optimization for adaptive sampling and reconstruction","volume":"31","author":"Li Tzu-Mao","year":"2012","unstructured":"Tzu-Mao Li, Yu-Ting Wu, and Yung-Yu Chuang. 2012b. SURE-based optimization for adaptive sampling and reconstruction. ACM Trans. Graphics (Proc. SIGGRAPH Asia) 31, 6, Article 194 (Nov. 2012), 9 pages.","journal-title":"ACM Trans. Graphics (Proc. SIGGRAPH Asia)"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37410"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2641762"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766992"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925936"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1661412.1618486"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024193"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366214"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12219"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-6858-5_26"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201388"},{"key":"e_1_2_1_33_1","unstructured":"Tiange Xiang Hongliang Yuan Haozhi Huang and Yujin Shi. 2021. Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool. arXiv:2103.16115 [cs.CV]"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14337"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14587"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:27:51Z","timestamp":1725496071000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555515"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1145\/3550454.3555515"],"URL":"https:\/\/doi.org\/10.1145\/3550454.3555515","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2022-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}