{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:31:43Z","timestamp":1778081503707,"version":"3.51.4"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:p>Inverse reconstruction from images is a central problem in many scientific and engineering disciplines. Recent progress on differentiable rendering has led to methods that can efficiently differentiate the full process of image formation with respect to millions of parameters to solve such problems via gradient-based optimization.<\/jats:p>\n          <jats:p>At the same time, the availability of cheap derivatives does not necessarily make an inverse problem easy to solve. Mesh-based representations remain a particular source of irritation: an adverse gradient step involving vertex positions could turn parts of the mesh inside-out, introduce numerous local self-intersections, or lead to inadequate usage of the vertex budget due to distortion. These types of issues are often irrecoverable in the sense that subsequent optimization steps will further exacerbate them. In other words, the optimization lacks robustness due to an objective function with substantial non-convexity.<\/jats:p>\n          <jats:p>Such robustness issues are commonly mitigated by imposing additional regularization, typically in the form of Laplacian energies that quantify and improve the smoothness of the current iterate. However, regularization introduces its own set of problems: solutions must now compromise between solving the problem and being smooth. Furthermore, gradient steps involving a Laplacian energy resemble Jacobi's iterative method for solving linear equations that is known for its exceptionally slow convergence.<\/jats:p>\n          <jats:p>We propose a simple and practical alternative that casts differentiable rendering into the framework of preconditioned gradient descent. Our pre-conditioner biases gradient steps towards smooth solutions without requiring the final solution to be smooth. In contrast to Jacobi-style iteration, each gradient step propagates information among all variables, enabling convergence using fewer and larger steps.<\/jats:p>\n          <jats:p>Our method is not restricted to meshes and can also accelerate the reconstruction of other representations, where smooth solutions are generally expected. We demonstrate its superior performance in the context of geometric optimization and texture reconstruction.<\/jats:p>","DOI":"10.1145\/3478513.3480501","type":"journal-article","created":{"date-parts":[[2021,12,10]],"date-time":"2021-12-10T18:29:20Z","timestamp":1639160960000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":136,"title":["Large steps in inverse rendering of geometry"],"prefix":"10.1145","volume":"40","author":[{"given":"Baptiste","family":"Nicolet","sequence":"first","affiliation":[{"name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"}]},{"given":"Alec","family":"Jacobson","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]},{"given":"Wenzel","family":"Jakob","sequence":"additional","affiliation":[{"name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2021,12,10]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417833"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280821"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186562.1015772"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1057432.1057457"},{"key":"e_1_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Mario Botsch Leif Kobbelt Mark Pauly Pierre Alliez and Bruno L\u00e9vy. 2010. Polygon Mesh Processing. A K Peters. http:\/\/www.crcpress.com\/product\/isbn\/9781568814261  Mario Botsch Leif Kobbelt Mark Pauly Pierre Alliez and Bruno L\u00e9vy. 2010. Polygon Mesh Processing. A K Peters. http:\/\/www.crcpress.com\/product\/isbn\/9781568814261","DOI":"10.1201\/b10688"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1391989.1391995"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13243"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311576"},{"key":"e_1_2_2_9_1","volume-title":"Partial differential equations and calculus of variations","author":"Dziuk Gerhard","unstructured":"Gerhard Dziuk . 1988. Finite elements for the Beltrami operator on arbitrary surfaces . In Partial differential equations and calculus of variations . Springer , 142--155. Gerhard Dziuk. 1988. Finite elements for the Beltrami operator on arbitrary surfaces. In Partial differential equations and calculus of variations. Springer, 142--155."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00874"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_42"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1455489"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2010.01765.x"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2005.08.011"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03179.x"},{"key":"e_1_2_2_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925920"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275109"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275047"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_11"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356510"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1174429.1174494"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.2969\/jmsj\/03720187"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392406"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356498"},{"key":"e_1_2_2_32_1","volume-title":"Laplacian Smoothing Gradient Descent. CoRR abs\/1806.06317","author":"Osher Stanley J.","year":"2018","unstructured":"Stanley J. Osher , Bao Wang , Penghang Yin , Xiyang Luo , Minh Pham , and Alex Tong Lin . 2018. Laplacian Smoothing Gradient Descent. CoRR abs\/1806.06317 ( 2018 ). arXiv:1806.06317 http:\/\/arxiv.org\/abs\/1806.06317 Stanley J. Osher, Bao Wang, Penghang Yin, Xiyang Luo, Minh Pham, and Alex Tong Lin. 2018. Laplacian Smoothing Gradient Descent. CoRR abs\/1806.06317 (2018). arXiv:1806.06317 http:\/\/arxiv.org\/abs\/1806.06317"},{"key":"e_1_2_2_33_1","volume-title":"Wise","author":"Park Jea-Hyun","year":"2021","unstructured":"Jea-Hyun Park , Abner J. Salgado , and Steven M . Wise . 2021 . Preconditioned accelerated gradient descent methods for locally Lipschitz smooth objectives with applications to the solution of nonlinear PDEs . arXiv:math.NA\/2006.06732 Jea-Hyun Park, Abner J. Salgado, and Steven M. Wise. 2021. Preconditioned accelerated gradient descent methods for locally Lipschitz smooth objectives with applications to the solution of nonlinear PDEs. arXiv:math.NA\/2006.06732"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"e_1_2_2_35_1","volume-title":"Computer graphics forum","author":"Patow Gustavo","unstructured":"Gustavo Patow and Xavier Pueyo . 2003. A survey of inverse rendering problems . In Computer graphics forum , Vol. 22 . Wiley Online Library , 663--687. Gustavo Patow and Xavier Pueyo. 2003. A survey of inverse rendering problems. In Computer graphics forum, Vol. 22. Wiley Online Library, 663--687."},{"key":"e_1_2_2_36_1","volume-title":"Computing discrete minimal surfaces and their conjugates. Experimental mathematics 2, 1","author":"Pinkall Ulrich","year":"1993","unstructured":"Ulrich Pinkall and Konrad Polthier . 1993. Computing discrete minimal surfaces and their conjugates. Experimental mathematics 2, 1 ( 1993 ), 15--36. Ulrich Pinkall and Konrad Polthier. 1993. Computing discrete minimal surfaces and their conjugates. Experimental mathematics 2, 1 (1993), 15--36."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.2983621"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383317"},{"key":"e_1_2_2_39_1","volume-title":"Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501","author":"Ravi Nikhila","year":"2020","unstructured":"Nikhila Ravi , Jeremy Reizenstein , David Novotny , Taylor Gordon , Wan-Yen Lo , Justin Johnson , and Georgia Gkioxari . 2020. Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501 ( 2020 ). Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501 (2020)."},{"key":"e_1_2_2_40_1","volume-title":"Symposium on Geometry Processing graduate school","volume":"2","author":"Solomon Justin","year":"2014","unstructured":"Justin Solomon , Keegan Crane , and Etienne Vouga . 2014 . Laplace-Beltrami: The Swiss army knife of geometry processing . In Symposium on Geometry Processing graduate school ( Cardiff, UK , 2014), Vol. 2 . Justin Solomon, Keegan Crane, and Etienne Vouga. 2014. Laplace-Beltrami: The Swiss army knife of geometry processing. In Symposium on Geometry Processing graduate school (Cardiff, UK, 2014), Vol. 2."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.2312\/egst.20051044"},{"key":"e_1_2_2_42_1","volume-title":"Computer Graphics Forum","author":"Sorkine Olga","unstructured":"Olga Sorkine . 2006. Differential representations for mesh processing . In Computer Graphics Forum , Vol. 25 . Wiley Online Library , 789--807. Olga Sorkine. 2006. Differential representations for mesh processing. In Computer Graphics Forum, Vol. 25. Wiley Online Library, 789--807."},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(88)90080-X"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459804"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459801"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01148"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439429"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459807"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459783"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392390"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356522"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201359"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478513.3480501","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3478513.3480501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:48Z","timestamp":1750191108000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478513.3480501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1145\/3478513.3480501"],"URL":"https:\/\/doi.org\/10.1145\/3478513.3480501","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"2021-12-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}