{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:44:13Z","timestamp":1777653853020,"version":"3.51.4"},"reference-count":29,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"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":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2024,5,11]]},"abstract":"<jats:p>We show how to transform a non-differentiable rasterizer into a differentiable one with minimal engineering efforts and no external dependencies (no Pytorch\/Tensorflow). We rely on Stochastic Gradient Estimation, a technique that consists of rasterizing after randomly perturbing the scene's parameters such that their gradient can be stochastically estimated and descended. This method is simple and robust but does not scale in dimensionality (number of scene parameters). Our insight is that the number of parameters contributing to a given rasterized pixel is bounded. Estimating and averaging gradients on a per-pixel basis hence bounds the dimensionality of the underlying optimization problem and makes the method scalable. Furthermore, it is simple to track per-pixel contributing parameters by rasterizing ID- and UV-buffers, which are trivial additions to a rasterization engine if not already available. With these minor modifications, we obtain an in-engine optimizer for 3D assets with millions of geometry and texture parameters.<\/jats:p>","DOI":"10.1145\/3651298","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T13:39:44Z","timestamp":1715607584000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Transforming a Non-Differentiable Rasterizer into a Differentiable One with Stochastic Gradient Estimation"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9675-3442","authenticated-orcid":false,"given":"Thomas","family":"Deliot","sequence":"first","affiliation":[{"name":"Intel Corporation, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9323-3318","authenticated-orcid":false,"given":"Eric","family":"Heitz","sequence":"additional","affiliation":[{"name":"Intel Corporation, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-0717","authenticated-orcid":false,"given":"Laurent","family":"Belcour","sequence":"additional","affiliation":[{"name":"Intel Corporation, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00255"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417833"},{"key":"e_1_2_1_3_1","first-page":"6","article-title":"SLANG.D: Fast, Modular and Differentiable Shader Programming","volume":"42","author":"Bangaru Sai","year":"2023","unstructured":"Sai Bangaru, Lifan Wu, Tzu-Mao Li, Jacob Munkberg, Gilbert Bernstein, Jonathan Ragan-Kelley, Fredo Durand, Aaron Lefohn, and Yong He. 2023. SLANG.D: Fast, Modular and Differentiable Shader Programming. ACM Transactions on Graphics (SIGGRAPH Asia) 42, 6 (December 2023), 1--28.","journal-title":"ACM Transactions on Graphics (SIGGRAPH Asia)"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496521"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4485(78)90110-0"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14381"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00417"},{"key":"e_1_2_1_8_1","volume-title":"Stochastic Gradient Estimation. Technical report","author":"Michael Fu.","year":"2005","unstructured":"Michael Fu. 2005. Stochastic Gradient Estimation. Technical report (2005)."},{"key":"e_1_2_1_9_1","volume-title":"Gradient Estimation Via Perturbation Analysis","author":"Glasserman Paul","unstructured":"Paul Glasserman. 1991. Gradient Estimation Via Perturbation Analysis. Norwell, MA:Kluwer."},{"key":"e_1_2_1_10_1","unstructured":"Jon Hasselgren Jacob Munkberg Jaakko Lehtinen Miika Aittala and Samuli Laine. 2021. Appearance-Driven Automatic 3D Model Simplification.. In EGSR (DL). 85--97."},{"key":"e_1_2_1_11_1","article-title":"Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering","volume":"41","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. Transactions on Graphics (Proceedings of SIGGRAPH) 41, 4 (2022).","journal-title":"Transactions on Graphics (Proceedings of SIGGRAPH)"},{"key":"e_1_2_1_12_1","article-title":"Hash Functions for GPU Rendering","volume":"9","author":"Jarzynski Mark","year":"2020","unstructured":"Mark Jarzynski and Marc Olano. 2020. Hash Functions for GPU Rendering. Journal of Computer Graphics Techniques (JCGT) 9, 3 (17 October 2020), 20--38.","journal-title":"Journal of Computer Graphics Techniques (JCGT)"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01001"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_1_16_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization.. In ICLR (Poster)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_2_1_18_1","volume-title":"Differentiable rendering with perturbed optimizers. Advances in Neural Information Processing Systems 34","author":"Lidec Quentin Le","year":"2021","unstructured":"Quentin Le Lidec, Ivan Laptev, Cordelia Schmid, and Justin Carpentier. 2021. Differentiable rendering with perturbed optimizers. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_2_1_19_1","article-title":"Differentiable Monte Carlo Ray Tracing through Edge Sampling","volume":"37","author":"Li Tzu-Mao","year":"2018","unstructured":"Tzu-Mao Li, Miika Aittala, Fr\u00e9do Durand, and Jaakko Lehtinen. 2018. Differentiable Monte Carlo Ray Tracing through Edge Sampling. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 37, 6 (2018), 222:1--222:11.","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_11"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356510"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356498"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.2687"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.94"},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459804","article-title":"Path replay backpropagation: differentiating light paths using constant memory and linear time","volume":"40","author":"Vicini Delio","year":"2021","unstructured":"Delio Vicini, S\u00e9bastien Speierer, and Wenzel Jakob. 2021. Path replay backpropagation: differentiating light paths using constant memory and linear time. ACM Transactions on Graphics (TOG) 40, 4 (2021), 1--14.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076536"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530080"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392383"}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651298","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:26:30Z","timestamp":1755912390000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651298"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,5,11]]}},"alternative-id":["10.1145\/3651298"],"URL":"https:\/\/doi.org\/10.1145\/3651298","relation":{},"ISSN":["2577-6193"],"issn-type":[{"value":"2577-6193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}