{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:42:53Z","timestamp":1779914573531,"version":"3.53.1"},"reference-count":82,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T00:00:00Z","timestamp":1625011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NVIDIA Fellowship"},{"name":"Ronald L. Graham Chair"},{"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":[[2021,6,30]]},"abstract":"<jats:p>In Computer Graphics, the two main approaches to rendering and visibility involve ray tracing and rasterization. However, a limitation of both approaches is that they essentially use point sampling. This is the source of noise and aliasing, and also leads to significant difficulties for differentiable rendering. In this work, we present a new rendering method, which we call vectorization, that computes 2D point-to-region integrals analytically, thus eliminating point sampling in the 2D integration domain such as for pixel footprints and area lights. Our vectorization revisits the concept of beam tracing, and handles the hidden surface removal problem robustly and accurately. That is, for each intersecting triangle inserted into the viewport of a beam in an arbitrary order, we are able to maintain all the visible regions formed by intersections and occlusions, thanks to our Visibility Bounding Volume Hierarchy structure. As a result, our vectorization produces perfectly anti-aliased visibility, accurate and analytic shading and shadows, and most important, fast and noise-free gradients with Automatic Differentiation or Finite Differences that directly enables differentiable rendering without any changes to our rendering pipeline. Our results are inherently high-quality and noise-free, and our gradients are one to two orders of magnitude faster than those computed with existing differentiable rendering methods.<\/jats:p>","DOI":"10.1145\/3452097","type":"journal-article","created":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T19:43:39Z","timestamp":1626378219000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Vectorization for Fast, Analytic, and Differentiable Visibility"],"prefix":"10.1145","volume":"40","author":[{"given":"Yang","family":"Zhou","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5735-0998","authenticated-orcid":false,"given":"Lifan","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California, San Diego and NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi","family":"Ramamoorthi","sequence":"additional","affiliation":[{"name":"University of California, San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling-Qi","family":"Yan","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,15]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/91394.91416"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808589"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03012.x"},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the Conference on Vision, Modeling, and Visualization. The Eurographics Association.","author":"Auzinger Thomas","year":"2013","unstructured":"Thomas Auzinger , Przemyslaw Musialski , Reinhold Preiner , and Michael Wimmer . 2013 a. Non-sampled anti-aliasing . In Proceedings of the Conference on Vision, Modeling, and Visualization. The Eurographics Association. Thomas Auzinger, Przemyslaw Musialski, Reinhold Preiner, and Michael Wimmer. 2013a. Non-sampled anti-aliasing. In Proceedings of the Conference on Vision, Modeling, and Visualization. The Eurographics Association."},{"key":"e_1_2_1_6_1","volume-title":"Analytic visibility on the GPU. Comput. Graph. Forum 32, 2pt4","author":"Auzinger Thomas","year":"2013","unstructured":"Thomas Auzinger , Michael Wimmer , and Stefan Jescke . 2013b. Analytic visibility on the GPU. Comput. Graph. Forum 32, 2pt4 ( 2013 ), 409\u2013418. Thomas Auzinger, Michael Wimmer, and Stefan Jescke. 2013b. Analytic visibility on the GPU. Comput. Graph. Forum 32, 2pt4 (2013), 409\u2013418."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417833"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/74334.74367"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/584458.584486"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/792757.792949"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/220279.220330"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/140954362"},{"key":"e_1_2_1_14_1","unstructured":"Bob Carpenter Matthew D. Hoffman Marcus Brubaker Daniel Lee Peter Li and Michael Betancourt. 2015. The Stan math library: Reverse-mode automatic differentiation in C++. Retrieved from https:\/\/arXiv:1509.07164.  Bob Carpenter Matthew D. Hoffman Marcus Brubaker Daniel Lee Peter Li and Michael Betancourt. 2015. The Stan math library: Reverse-mode automatic differentiation in C++. Retrieved from https:\/\/arXiv:1509.07164."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/965139.807360"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808586"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01501.x"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/253284.253312"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02063.x"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3231578.3231584"},{"key":"e_1_2_1_21_1","volume-title":"Mark Overmars, and Otfried Schwarzkopf.","author":"de Berg Mark","year":"1997","unstructured":"Mark de Berg , Marc Van Kreveld , Mark Overmars, and Otfried Schwarzkopf. 1997 . Computational Geometry. Springer-Verlag . Mark de Berg, Marc Van Kreveld, Mark Overmars, and Otfried Schwarzkopf. 1997. Computational Geometry. Springer-Verlag."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1811158.1811181"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2664591.2664610"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/338219.338657"},{"key":"e_1_2_1_26_1","unstructured":"Jon Ferraiolo Fujisawa Jun and Dean Jackson. 2000. Scalable Vector Graphics (SVG) 1.0 Specification.  Jon Ferraiolo Fujisawa Jun and Dean Jackson. 2000. Scalable Vector Graphics (SVG) 1.0 Specification."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/304893.304911"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/0925-7721(95)00022-2"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/1049-9652(92)90029-W"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0097-8493(99)00088-6"},{"key":"e_1_2_1_31_1","volume-title":"Beno\u00eet Jacob et\u00a0al","author":"Guennebaud Ga\u00ebl","year":"2010","unstructured":"Ga\u00ebl Guennebaud , Beno\u00eet Jacob et\u00a0al . 2010 . Eigen v3. Retrieved from http:\/\/eigen.tuxfamily.org. Ga\u00ebl Guennebaud, Beno\u00eet Jacob et\u00a0al. 2010. Eigen v3. Retrieved from http:\/\/eigen.tuxfamily.org."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383654.2383685"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808588"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766988"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925895"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/262839.262847"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311555"},{"key":"e_1_2_1_38_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_1_39_1","volume-title":"Enoki: Structured vectorization and differentiation on modern processor architectures.","author":"Jakob Wenzel","year":"2019","unstructured":"Wenzel Jakob . 2019 . Enoki: Structured vectorization and differentiation on modern processor architectures. Retrieved from https:\/\/github.com\/mitsuba-renderer\/enoki. Wenzel Jakob. 2019. Enoki: Structured vectorization and differentiation on modern processor architectures. Retrieved from https:\/\/github.com\/mitsuba-renderer\/enoki."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/1032643.1033079"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/0925-7721(92)90024-M"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comgeo.2007.06.003"},{"key":"e_1_2_1_43_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201915)","author":"Diederick","unstructured":"Diederick P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization . In Proceedings of the International Conference on Learning Representations (ICLR\u201915) . Diederick P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR\u201915)."},{"key":"e_1_2_1_44_1","volume-title":"ARB multisample. OpenGL Extension Registry","author":"Kirkland Dale","year":"2002","unstructured":"Dale Kirkland , Bill Armstrong , Michael Gold , Jon Leech , and Paula Womack . 2002. ARB multisample. OpenGL Extension Registry ( 2002 ), 83\u201394. Dale Kirkland, Bill Armstrong, Michael Gold, Jon Leech, and Paula Womack. 2002. ARB multisample. OpenGL Extension Registry (2002), 83\u201394."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jlap.2004.07.006"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275109"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417871"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01905.x"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3112655.3112866"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356510"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13138"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12070"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/27625.27627"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/204865.204889"},{"key":"e_1_2_1_57_1","unstructured":"Philipp Moritz Robert Nishihara and Michael Jordan. 2016. A linearly-convergent stochastic L-BFGS algorithm. In Proceeding sof the Conference on Artificial Intelligence and Statistics. 249\u2013258.  Philipp Moritz Robert Nishihara and Michael Jordan. 2016. A linearly-convergent stochastic L-BFGS algorithm. In Proceeding sof the Conference on Artificial Intelligence and Statistics. 249\u2013258."},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/74334.74372"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(05)80067-4"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392406"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383533.2383562"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/581896.581921"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12257"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01935366"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.5555\/521378"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/1399504.1360691"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383847.2383861"},{"key":"e_1_2_1_68_1","unstructured":"Nikhila Ravi Jeremy Reizenstein David Novotny Taylor Gordon Wan-Yen Lo Justin Johnson and Georgia Gkioxari. 2020. Accelerating 3D deep learning with PyTorch3D. Retrieved from https:\/\/arXiv:2007.08501.  Nikhila Ravi Jeremy Reizenstein David Novotny Taylor Gordon Wan-Yen Lo Justin Johnson and Georgia Gkioxari. 2020. Accelerating 3D deep learning with PyTorch3D. Retrieved from https:\/\/arXiv:2007.08501."},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/102377.112141"},{"key":"e_1_2_1_71_1","volume-title":"Lecture notes on geometric robustness. Retreived on","author":"Shewchuk Jonathan Richard","year":"2020","unstructured":"Jonathan Richard Shewchuk . 2013. Lecture notes on geometric robustness. Retreived on December 2020 from https:\/\/people.eecs.berkeley.edu\/\u223cjrs\/meshpapers\/robnotes.pdf. Jonathan Richard Shewchuk. 2013. Lecture notes on geometric robustness. Retreived on December 2020 from https:\/\/people.eecs.berkeley.edu\/\u223cjrs\/meshpapers\/robnotes.pdf."},{"key":"e_1_2_1_72_1","volume-title":"Proceedings of the Eurographics Workshop on Rendering Techniques (EGWR\u201998)","author":"James Stewart A.","year":"1998","unstructured":"A. James Stewart and Tasso Karkanis . 1998 . Computing the approximate visibility map, with applications to form factors and discontinuity meshing . In Proceedings of the Eurographics Workshop on Rendering Techniques (EGWR\u201998) . 57\u201368. A. James Stewart and Tasso Karkanis. 1998. Computing the approximate visibility map, with applications to form factors and discontinuity meshing. In Proceedings of the Eurographics Workshop on Rendering Techniques (EGWR\u201998). 57\u201368."},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/356625.356626"},{"key":"e_1_2_1_74_1","volume-title":"CGAL User and Reference Manual (5.0.2 ed.)","author":"Project The CGAL","unstructured":"The CGAL Project . 2020. CGAL User and Reference Manual (5.0.2 ed.) . CGAL Editorial Board. Retrieved from https:\/\/doc.cgal.org\/5.0.2\/Manual\/packages.html. The CGAL Project. 2020. CGAL User and Reference Manual (5.0.2 ed.). CGAL Editorial Board. Retrieved from https:\/\/doc.cgal.org\/5.0.2\/Manual\/packages.html."},{"key":"e_1_2_1_75_1","volume-title":"Goodman","author":"Toth Csaba D.","year":"2017","unstructured":"Csaba D. Toth , Joseph O\u2019Rourke , and Jacob E . Goodman . 2017 . Handbook of Discrete and Computational Geometry. Chapman and Hall\/CRC. Csaba D. Toth, Joseph O\u2019Rourke, and Jacob E. Goodman. 2017. Handbook of Discrete and Computational Geometry. Chapman and Hall\/CRC."},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2790060.2790068"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/97880.97920"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/965141.563896"},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322936"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3023368.3023370"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14018"},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1016\/0925-7721(95)00040-2"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459782"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356522"},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2721400"},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980228"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3452097","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3452097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:07Z","timestamp":1750193287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3452097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,30]]},"references-count":82,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,6,30]]}},"alternative-id":["10.1145\/3452097"],"URL":"https:\/\/doi.org\/10.1145\/3452097","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,30]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}