{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T05:33:07Z","timestamp":1774243987247,"version":"3.50.1"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ERC Starting Grant LEGO3D","award":["850533"],"award-info":[{"award-number":["850533"]}]},{"name":"DFG EXC","award":["number 2064\/1 - project number 390727645"],"award-info":[{"award-number":["number 2064\/1 - project number 390727645"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2024,7,19]]},"abstract":"<jats:p>While surface-based view synthesis algorithms are appealing due to their low computational requirements, they often struggle to reproduce thin structures. In contrast, more expensive methods that model the scene's geometry as a volumetric density field (e.g. NeRF) excel at reconstructing fine geometric detail. However, density fields often represent geometry in a \"fuzzy\" manner, which hinders exact localization of the surface. In this work, we modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. First, we employ a discrete opacity grid representation instead of a continuous density field, which allows opacity values to discontinuously transition from zero to one at the surface. Second, we anti-alias by casting multiple rays per pixel, which allows occlusion boundaries and subpixel structures to be modelled without using semi-transparent voxels. Third, we minimize the binary entropy of the opacity values, which facilitates the extraction of surface geometry by encouraging opacity values to binarize towards the end of training. Lastly, we develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices and achieve significantly higher view synthesis quality compared to existing mesh-based approaches. Our interactive webdemo is available at https:\/\/binary-opacity-grid.github.io.<\/jats:p>","DOI":"10.1145\/3658130","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T14:47:57Z","timestamp":1721400477000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1050-3958","authenticated-orcid":false,"given":"Christian","family":"Reiser","sequence":"first","affiliation":[{"name":"T\u00fcbingen AI Center, University of T\u00fcbingen, T\u00fcbingen, Germany"},{"name":"Google Research, T\u00fcbingen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5005-8110","authenticated-orcid":false,"given":"Stephan","family":"Garbin","sequence":"additional","affiliation":[{"name":"Google Research, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8268-3285","authenticated-orcid":false,"given":"Pratul","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Google Research, San Francisco, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8798-3270","authenticated-orcid":false,"given":"Dor","family":"Verbin","sequence":"additional","affiliation":[{"name":"Google Research, San Francisco, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5300-5475","authenticated-orcid":false,"given":"Richard","family":"Szeliski","sequence":"additional","affiliation":[{"name":"Google Research, Seattle, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9796-6121","authenticated-orcid":false,"given":"Ben","family":"Mildenhall","sequence":"additional","affiliation":[{"name":"Google Research, San Francisco, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4016-9448","authenticated-orcid":false,"given":"Jonathan","family":"Barron","sequence":"additional","affiliation":[{"name":"Google Research, San Francisco, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2182-0185","authenticated-orcid":false,"given":"Peter","family":"Hedman","sequence":"additional","affiliation":[{"name":"Google Research, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-3726","authenticated-orcid":false,"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[{"name":"T\u00fcbingen AI Center, University of T\u00fcbingen, T\u00fcbingen, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,7,19]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566652"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3203192"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","unstructured":"Zhiqin Chen Thomas Funkhouser Peter Hedman and Andrea Tagliasacchi. 2023. MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 16569--16578. 10.1109\/CVPR52729.2023.01590","DOI":"10.1109\/CVPR52729.2023.01590"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/893689"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0450(1979)018"},{"key":"e_1_2_2_10_1","volume-title":"Barron","author":"Duckworth Daniel","year":"2023","unstructured":"Daniel Duckworth, Peter Hedman, Christian Reiser, Peter Zhizhin, Jean-Fran\u00e7ois Thibert, Mario Lu\u010di\u0107, Richard Szeliski, and Jonathan T. Barron. 2023. SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration. arXiv:2312.07541 [cs.CV]"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258849"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618161"},{"key":"e_1_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Antoine Gu\u00e9don and Vincent Lepetit. 2023. SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. arXiv:2311.12775 [cs.GR]","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"e_1_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Binbin Huang Zehao Yu Anpei Chen Andreas Geiger and Shenghua Gao. 2024. 2D Gaussian Splatting for Geometrically Accurate Radiance Fields. arXiv:2403.17888 [cs.CV]","DOI":"10.1145\/3641519.3657428"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995693"},{"key":"e_1_2_2_19_1","unstructured":"Brian Karis. 2014. High Quality Temporal Supersampling. ACM SIGGRAPH Courses: Advances in Real-Time Rendering in Games."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_2_21_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2017","unstructured":"Diederik P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs.LG]"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14339"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141926"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00308"},{"key":"e_1_2_2_26_1","volume-title":"Lin (Eds.)","volume":"33","author":"Liu Lingjie","year":"2020","unstructured":"Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. 2020. Neural Sparse Voxel Fields. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 15651--15663. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/b4b758962f17808746e9bb832a6fa4b8-Paper.pdf"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323020"},{"key":"e_1_2_2_28_1","unstructured":"Xiaoyang Lyu Yang-Tian Sun Yi-Hua Huang Xiuzhe Wu Ziyi Yang Yilun Chen Jiangmiao Pang and Xiaojuan Qi. 2024. 3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting. arXiv:2404.00409 [cs.CV]"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00810"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469842"},{"key":"e_1_2_2_35_1","volume-title":"Michael Niemeyer, Abhijit Kundu, and Federico Tombari.","author":"Rakotosaona Marie-Julie","year":"2023","unstructured":"Marie-Julie Rakotosaona, Fabian Manhardt, Diego Martin Arroyo, Michael Niemeyer, Abhijit Kundu, and Federico Tombari. 2023. NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes. 3DV (2023)."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592426"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01204"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530122"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530121"},{"key":"e_1_2_2_40_1","volume-title":"Game Developers Conference.","author":"Salvi Marco","year":"2016","unstructured":"Marco Salvi. 2016. An excursion in temporal supersampling. Game Developers Conference."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"e_1_2_2_42_1","volume-title":"Advances in Neural Information Processing Systems","author":"Shen Tianchang","year":"2021","unstructured":"Tianchang Shen, Jun Gao, Kangxue Yin, Ming-Yu Liu, and Sanja Fidler. 2021. Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 6087--6101. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/30a237d18c50f563cba4531f1db44acf-Paper.pdf"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592430"},{"key":"e_1_2_2_44_1","volume-title":"Nuvo: Neural UV Mapping for Unruly 3D Representations. arXiv:2312.05283 [cs.CV]","author":"Srinivasan Pratul P.","year":"2023","unstructured":"Pratul P. Srinivasan, Stephan J. Garbin, Dor Verbin, Jonathan T. Barron, and Ben Mildenhall. 2023. Nuvo: Neural UV Mapping for Unruly 3D Representations. arXiv:2312.05283 [cs.CV]"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01626"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_2_2_47_1","volume-title":"Lorenzo Porzi, Peter Kontschieder, Deva Ramanan, Michael Zollh\u00f6fer, and Christian Richardt.","author":"Turki Haithem","year":"2023","unstructured":"Haithem Turki, Vasu Agrawal, Samuel Rota Bul\u00f2, Lorenzo Porzi, Peter Kontschieder, Deva Ramanan, Michael Zollh\u00f6fer, and Christian Richardt. 2023. HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces. arXiv:2312.03160 [cs.CV]"},{"key":"e_1_2_2_48_1","volume-title":"Unke and Hartmut Maennel","author":"Oliver","year":"2024","unstructured":"Oliver T. Unke and Hartmut Maennel. 2024. E3x: E(3)-Equivariant Deep Learning Made Easy. arXiv (2024)."},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_54"},{"key":"e_1_2_2_50_1","volume-title":"NeuS: Learning Neural Implicit Surfaces by","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 27171--27183. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/e41e164f7485ec4a28741a2d0ea41c74-Paper.pdf"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00305"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618390"},{"key":"e_1_2_2_53_1","unstructured":"Yaniv Wolf Amit Bracha and Ron Kimmel. 2024. Surface Reconstruction from Gaussian Splatting via Novel Stereo Views. arXiv:2404.01810 [cs.CV]"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344925"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00609"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00017"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14018"},{"key":"e_1_2_2_59_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Yariv Lior","year":"2021","unstructured":"Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume Rendering of Neural Implicit Surfaces. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 4805--4815. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/25e2a30f44898b9f3e978b1786dcd85c-Paper.pdf"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591536"},{"key":"e_1_2_2_61_1","volume-title":"Lin (Eds.)","volume":"33","author":"Yariv Lior","year":"2020","unstructured":"Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon, Basri Ronen, and Yaron Lipman. 2020. Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 2492--2502. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1a77befc3b608d6ed363567685f70e1e-Paper.pdf"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"e_1_2_2_63_1","unstructured":"Mulin Yu Tao Lu Linning Xu Lihan Jiang Yuanbo Xiangli and Bo Dai. 2024a. GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction. arXiv:2403.16964 [cs.CV]"},{"key":"e_1_2_2_64_1","unstructured":"Zehao Yu Anpei Chen Bozidar Antic Songyou Peng Apratim Bhattacharyya Michael Niemeyer Siyu Tang Torsten Sattler and Andreas Geiger. 2022a. SDFStudio: A Unified Framework for Surface Reconstruction. https:\/\/github.com\/autonomousvision\/sdfstudio"},{"key":"e_1_2_2_65_1","volume-title":"Advances in Neural Information Processing Systems","author":"Yu Zehao","year":"2022","unstructured":"Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, and Andreas Geiger. 2022b. MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 25018--25032. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/9f0b1220028dfa2ee82ca0a0e0fc52d1-Paper-Conference.pdf"},{"key":"e_1_2_2_66_1","unstructured":"Zehao Yu Torsten Sattler and Andreas Geiger. 2024b. Gaussian Opacity Fields: Efficient and Compact Surface Reconstruction in Unbounded Scenes. arXiv:2404.10772 [cs.CV]"},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618197"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658130","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:54Z","timestamp":1750291554000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,19]]},"references-count":67,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7,19]]}},"alternative-id":["10.1145\/3658130"],"URL":"https:\/\/doi.org\/10.1145\/3658130","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,19]]},"assertion":[{"value":"2024-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}