{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:29:40Z","timestamp":1776832180879,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730679","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Neural BRDF Importance Sampling by Reparameterization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2773-2032","authenticated-orcid":false,"given":"Liwen","family":"Wu","sequence":"first","affiliation":[{"name":"University of California San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0311-2521","authenticated-orcid":false,"given":"Sai","family":"Bi","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8487-8018","authenticated-orcid":false,"given":"Zexiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hillbot, San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9755-9040","authenticated-orcid":false,"given":"Hao","family":"Tan","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1727-1689","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5926-6266","authenticated-orcid":false,"given":"Fujun","family":"Luan","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2595-2493","authenticated-orcid":false,"given":"Haolin","family":"Lu","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3993-5789","authenticated-orcid":false,"given":"Ravi","family":"Ramamoorthi","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14449"},{"key":"e_1_3_3_2_3_1","unstructured":"Yaoyi Bai Songyin Wu Zheng Zeng Beibei Wang and Ling-Qi Yan. 2022. BSDF Importance Baking: A Lightweight Neural Solution to Importance Sampling General Parametric BSDFs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.13681 (2022)."},{"key":"e_1_3_3_2_4_1","volume-title":"NeurIPS","author":"Chen Ricky\u00a0TQ","year":"2018","unstructured":"Ricky\u00a0TQ Chen, Yulia Rubanova, Jesse Bettencourt, and David\u00a0K Duvenaud. 2018. Neural ordinary differential equations. In NeurIPS."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01166.x"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/357290.357293"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/300776.300778"},{"key":"e_1_3_3_2_8_1","unstructured":"Laurent Dinh David Krueger and Yoshua Bengio. 2014. Nice: Non-linear independent components estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1410.8516 (2014)."},{"key":"e_1_3_3_2_9_1","volume-title":"ICLR","author":"Dinh Laurent","year":"2022","unstructured":"Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. 2022. Density estimation using Real NVP. In ICLR."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14051"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14846"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14428"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00415"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14867"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275059"},{"key":"e_1_3_3_2_16_1","volume-title":"NeurIPS","author":"Durkan Conor","year":"2019","unstructured":"Conor Durkan, Artur Bekasov, Iain Murray, and George Papamakarios. 2019. Neural spline flows. In NeurIPS."},{"key":"e_1_3_3_2_17_1","volume-title":"Neural networks","author":"Elfwing Stefan","year":"2018","unstructured":"Stefan Elfwing, Eiji Uchibe, and Kenji Doya. 2018. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. In Neural networks."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530732"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591505"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687684"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Pascal Grittmann Iliyan Georgiev Philipp Slusallek and Jaroslav K\u0159iv\u00e1nek. 2019. Variance-aware multiple importance sampling.","DOI":"10.1145\/3355089.3356515"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14060"},{"key":"e_1_3_3_2_23_1","volume-title":"JCGT","author":"Heitz Eric","year":"2018","unstructured":"Eric Heitz. 2018. Sampling the ggx distribution of visible normals. In JCGT."},{"key":"e_1_3_3_2_24_1","volume-title":"SIGGRAPH","author":"Heitz Eric","year":"2023","unstructured":"Eric Heitz, Laurent Belcour, and Thomas Chambon. 2023. Iterative \u03b1 -(de) blending: A minimalist deterministic diffusion model. In SIGGRAPH."},{"key":"e_1_3_3_2_25_1","volume-title":"EGSR (EI&I)","author":"Herholz Sebastian","year":"2018","unstructured":"Sebastian Herholz, Oskar Elek, Jens Schindel, Jaroslav Kriv\u00e1nek, and Hendrik\u00a0PA Lensch. 2018. A Unified Manifold Framework for Efficient BRDF Sampling based on Parametric Mixture Models.. In EGSR (EI&I)."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12950"},{"key":"e_1_3_3_2_27_1","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS."},{"key":"e_1_3_3_2_28_1","volume-title":"ACM ToG","author":"Jakob Wenzel","year":"2022","unstructured":"Wenzel Jakob, S\u00e9bastien Speierer, Nicolas Roussel, and Delio Vicini. 2022. Dr. jit: A just-in-time compiler for differentiable rendering. In ACM ToG."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_3_3_2_30_1","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6980 (2014)."},{"key":"e_1_3_3_2_31_1","volume-title":"IEEE transactions on pattern analysis and machine intelligence","author":"Kobyzev Ivan","year":"2020","unstructured":"Ivan Kobyzev, Simon\u00a0JD Prince, and Marcus\u00a0A Brubaker. 2020. Normalizing flows: An introduction and review of current methods. In IEEE transactions on pattern analysis and machine intelligence."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459795"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530721"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186562.1015751"},{"key":"e_1_3_3_2_35_1","volume-title":"ICLR","author":"Lipman Yaron","year":"2022","unstructured":"Yaron Lipman, Ricky\u00a0TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matthew Le. 2022. Flow Matching for Generative Modeling. In ICLR."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687566"},{"key":"e_1_3_3_2_37_1","volume-title":"ICLR","author":"Liu Xingchao","year":"2022","unstructured":"Xingchao Liu, Chengyue Gong, et\u00a0al. 2022. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow. In ICLR."},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13227"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341156"},{"key":"e_1_3_3_2_41_1","volume-title":"ACM ToG","author":"Mullia Krishna","year":"2024","unstructured":"Krishna Mullia, Fujun Luan, Xin Sun, and Milo\u0161 Ha\u0161an. 2024. RNA: Relightable Neural Assets. In ACM ToG."},{"key":"e_1_3_3_2_42_1","volume-title":"NeurIPs","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. Pytorch: An imperative style, high-performance deep learning library. In NeurIPs."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13921"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13633"},{"key":"e_1_3_3_2_45_1","unstructured":"Prajit Ramachandran Barret Zoph and Quoc\u00a0V Le. 2017. Searching for activation functions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.05941 (2017)."},{"key":"e_1_3_3_2_46_1","volume-title":"ICML","author":"Rezende Danilo","year":"2015","unstructured":"Danilo Rezende and Shakir Mohamed. 2015. Variational inference with normalizing flows. In ICML."},{"key":"e_1_3_3_2_47_1","volume-title":"NeurIPS","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. In NeurIPS."},{"key":"e_1_3_3_2_48_1","volume-title":"ICLR","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik\u00a0P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. In ICLR."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14335"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15234"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15158"},{"key":"e_1_3_3_2_52_1","unstructured":"Aaron Van\u00a0den Oord Nal Kalchbrenner Lasse Espeholt Oriol Vinyals Alex Graves et\u00a0al. 2016. Conditional image generation with pixelcnn decoders."},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218498"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601203"},{"key":"e_1_3_3_2_55_1","volume-title":"EGSR","author":"Walter Bruce","year":"2007","unstructured":"Bruce Walter, Stephen\u00a0R Marschner, Hongsong Li, and Kenneth\u00a0E Torrance. 2007. Microfacet models for refraction through rough surfaces. In EGSR."},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Rex West Iliyan Georgiev Adrien Gruson and Toshiya Hachisuka. 2020. Continuous multiple importance sampling. ACM ToG (2020).","DOI":"10.1145\/3386569.3392436"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555388"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306307.3328144"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591524"},{"key":"e_1_3_3_2_60_1","volume-title":"ACM Computing Surveys","author":"Yang Ling","year":"2023","unstructured":"Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Wentao Zhang, Bin Cui, and Ming-Hsuan Yang. 2023. Diffusion models: A comprehensive survey of methods and applications. In ACM Computing Surveys."},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3659577"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459810"},{"key":"e_1_3_3_2_64_1","volume-title":"ACM ToG","author":"Zhu Shilin","year":"2021","unstructured":"Shilin Zhu, Zexiang Xu, Tiancheng Sun, Alexandr Kuznetsov, Mark Meyer, Henrik\u00a0Wann Jensen, Hao Su, and Ravi Ramamoorthi. 2021b. Photon-driven neural reconstruction for path guiding. In ACM ToG."}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:54:48Z","timestamp":1774018488000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":63,"alternative-id":["10.1145\/3721238.3730679","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730679","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}