{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:22:18Z","timestamp":1782318138685,"version":"3.54.5"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology"},{"name":"Research Grant of Beijing Higher In- stitution Engineering Research Center"},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2021ZD0112902"],"award-info":[{"award-number":["2021ZD0112902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:p>To reconstruct meshes from the widely-available 3D point cloud data, implicit shape representation is among the primary choices as an intermediate form due to its superior representation power and robustness in topological optimizations. Although different parameterizations of the implicit fields have been explored to model the underlying geometry, there is no explicit mechanism to ensure the fitting tightness of the surface to the input. We present in response, NeuralGalerkin, a neural Galerkin-method-based solver designed for reconstructing highly-accurate surfaces from the input point clouds. NeuralGalerkin internally discretizes the target implicit field as a linear combination of a set of spatially-varying basis functions inferred by an adaptive sparse convolution neural network. It then solves differentiably for a variational problem that incorporates both positional and normal constraints from the data in closed form within a single forward pass, highly respecting the raw input points. The reconstructed surface extracted from the implicit interpolants is hence very accurate and incorporates useful inductive biases benefiting from the training data. Extensive evaluations on various datasets demonstrate our method's promising reconstruction performance and scalability.<\/jats:p>","DOI":"10.1145\/3550454.3555457","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T21:19:07Z","timestamp":1669843147000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":56,"title":["A Neural Galerkin Solver for Accurate Surface Reconstruction"],"prefix":"10.1145","volume":"41","author":[{"given":"Jiahui","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Xiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530141"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00264"},{"key":"e_1_2_2_3_1","volume-title":"SALD: Sign Agnostic Learning with Derivatives. In Int. Conf. Learning Representations.","author":"Atzmon Matan","year":"2020","unstructured":"Matan Atzmon and Yaron Lipman. 2020b. SALD: Sign Agnostic Learning with Derivatives. In Int. Conf. Learning Representations."},{"key":"e_1_2_2_4_1","volume-title":"Neural RGB-D surface reconstruction. arXiv preprint arXiv:2104.04532","author":"Azinovi\u0107 Dejan","year":"2021","unstructured":"Dejan Azinovi\u0107, Ricardo Martin-Brualla, Dan B Goldman, Matthias Nie\u00dfner, and Justus Thies. 2021. Neural RGB-D surface reconstruction. arXiv preprint arXiv:2104.04532 (2021)."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_2"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.591"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02058.x"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383266"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_2_2_11_1","volume-title":"Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012","author":"Chang Angel X","year":"2015","unstructured":"Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)."},{"key":"e_1_2_2_12_1","volume-title":"CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene. In European Conf. Computer Vision. Springer, 1000--1010","author":"Chen Haoxiang","year":"2022","unstructured":"Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu, and Shi-Min Hu. 2022. CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene. In European Conf. Computer Vision. Springer, 1000--1010."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01284"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00700"},{"key":"e_1_2_2_15_1","first-page":"21638","article-title":"Neural unsigned distance fields for implicit function learning","volume":"33","author":"Chibane Julian","year":"2020","unstructured":"Julian Chibane, Gerard Pons-Moll, et al. 2020b. Neural unsigned distance fields for implicit function learning. NeurIPS 33 (2020), 21638--21652.","journal-title":"NeurIPS"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_7"},{"key":"e_1_2_2_19_1","volume-title":"Int. Conf. Machine Learning. PMLR, 1126--1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Int. Conf. Machine Learning. PMLR, 1126--1135."},{"key":"e_1_2_2_20_1","first-page":"897","article-title":"On electrical circuits for the approximate solution of the Laplace equation","volume":"19","author":"Galerkin BG","year":"1915","unstructured":"BG Galerkin. 1915. On electrical circuits for the approximate solution of the Laplace equation. Vestnik Inzh 19 (1915), 897--908.","journal-title":"Vestnik Inzh"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00491"},{"key":"e_1_2_2_23_1","volume-title":"Deep Structured Implicit Functions. arXiv preprint arXiv:1912.06126","author":"Genova Kyle","year":"2019","unstructured":"Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, and Thomas A Funkhouser. 2019. Deep Structured Implicit Functions. arXiv preprint arXiv:1912.06126 (2019)."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"e_1_2_2_25_1","volume-title":"Implicit Geometric Regularization for Learning Shapes. In Int. Conf. Machine Learning. PMLR, 3789--3799","author":"Gropp Amos","year":"2020","unstructured":"Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, and Yaron Lipman. 2020. Implicit Geometric Regularization for Learning Shapes. In Int. Conf. Machine Learning. PMLR, 3789--3799."},{"key":"e_1_2_2_26_1","volume-title":"MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks. arXiv preprint arXiv:2111.14549","author":"Guillard Benoit","year":"2021","unstructured":"Benoit Guillard, Federico Stella, and Pascal Fua. 2021. MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks. arXiv preprint arXiv:2111.14549 (2021)."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392415"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3097-4"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00882"},{"key":"e_1_2_2_30_1","volume-title":"Surface Reconstruction from Point Clouds: A Survey and a Benchmark. arXiv preprint arXiv:2205.02413","author":"Huang Zhangjin","year":"2022","unstructured":"Zhangjin Huang, Yuxin Wen, Zihao Wang, Jinjuan Ren, and Kui Jia. 2022. Surface Reconstruction from Point Clouds: A Survey and a Benchmark. arXiv preprint arXiv:2205.02413 (2022)."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00604"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2020.v20.n4.a1"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487237"},{"key":"e_1_2_2_34_1","volume-title":"Proceedings of the Fourth Eurographics Symposium on Geometry Processing","volume":"70","author":"Kazhdan Michael M.","year":"2006","unstructured":"Michael M. Kazhdan, Matthew Bolitho, and Hugues Hoppe. 2006. Poisson surface reconstruction. In Proceedings of the Fourth Eurographics Symposium on Geometry Processing, Cagliari, Sardinia, Italy, June 26--28, 2006 (ACM International Conference Proceeding Series, Vol. 256), Alla Sheffer and Konrad Polthier (Eds.). Eurographics Association, 61--70."},{"key":"e_1_2_2_35_1","volume-title":"High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review. Computational Visual Media","author":"Li Jianwei","year":"2022","unstructured":"Jianwei Li, Wei Gao, Yihong Wu, Yangdong Liu, and Yanfei Shen. 2022. High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review. Computational Visual Media (2022), 1--25."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00308"},{"key":"e_1_2_2_37_1","volume-title":"Int. Conf. Machine Learning. PMLR, 6702--6712","author":"Lipman Yaron","year":"2021","unstructured":"Yaron Lipman. 2021. Phase Transitions, Distance Functions, and Implicit Neural Representations. In Int. Conf. Machine Learning. PMLR, 6702--6712."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00183"},{"key":"e_1_2_2_39_1","first-page":"163","article-title":"Marching cubes: A high resolution 3D surface construction algorithm","volume":"21","author":"Lorensen William E","year":"1987","unstructured":"William E Lorensen and Harvey E Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm. ACM Trans. Graph. 21, 4 (1987), 163--169.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459785"},{"key":"e_1_2_2_41_1","volume-title":"Geometric modeling using octree encoding. Computer graphics and image processing 19, 2","author":"Meagher Donald","year":"1982","unstructured":"Donald Meagher. 1982. Geometric modeling using octree encoding. Computer graphics and image processing 19, 2 (1982), 129--147."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487235"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882293"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2003.12.002"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_2_2_48_1","first-page":"13032","article-title":"Shape as points: A differentiable poisson solver","volume":"34","author":"Peng Songyou","year":"2021","unstructured":"Songyou Peng, Chiyu Jiang, Yiyi Liao, Michael Niemeyer, Marc Pollefeys, and Andreas Geiger. 2021. Shape as points: A differentiable poisson solver. NeurIPS 34 (2021), 13032--13044.","journal-title":"NeurIPS"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"e_1_2_2_50_1","volume-title":"Proc. IEEE Conf. CVPR. 652--660","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proc. IEEE Conf. CVPR. 652--660."},{"key":"e_1_2_2_51_1","volume-title":"On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237","author":"Reddi Sashank J","year":"2019","unstructured":"Sashank J Reddi, Satyen Kale, and Sanjiv Kumar. 2019. On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237 (2019)."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.1996.568127"},{"key":"e_1_2_2_53_1","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume":"33","author":"Sitzmann Vincent","year":"2020","unstructured":"Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. 2020. Implicit neural representations with periodic activation functions. NeurIPS 33 (2020), 7462--7473.","journal-title":"NeurIPS"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0230-z"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"e_1_2_2_56_1","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, and Ren Ng. 2020. Fourier features let networks learn high frequency functions in low dimensional domains. NeurIPS 33 (2020), 7537--7547.","journal-title":"NeurIPS"},{"key":"e_1_2_2_57_1","volume-title":"TorchSparse: Efficient Point Cloud Inference Engine. In Conference on Machine Learning and Systems (MLSys).","author":"Tang Haotian","year":"2022","unstructured":"Haotian Tang, Zhijian Liu, Xiuyu Li, Yujun Lin, and Song Han. 2022. TorchSparse: Efficient Point Cloud Inference Engine. In Conference on Machine Learning and Systems (MLSys)."},{"key":"e_1_2_2_58_1","volume-title":"Proc. IEEE Int. Conf. Computer Vision. 6504--6513","author":"Tang Jiapeng","year":"2021","unstructured":"Jiapeng Tang, Jiabao Lei, Dan Xu, Feiying Ma, Kui Jia, and Lei Zhang. 2021b. SAConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks. In Proc. IEEE Int. Conf. Computer Vision. 6504--6513."},{"key":"e_1_2_2_59_1","unstructured":"Jia-Heng Tang Weikai Chen Bo Wang Songrun Liu Bo Yang Lin Gao et al. 2021a. OctField: Hierarchical Implicit Functions for 3D Modeling. NeurIPS 34 (2021)."},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00560"},{"key":"e_1_2_2_62_1","volume-title":"Nature Vectors by Vecteezy. Retrieved","year":"2022","unstructured":"Vecteezy. 2022. Nature Vectors by Vecteezy. Retrieved May 1, 2022 from https:\/\/www.vecteezy.com\/free-vector\/nature"},{"key":"e_1_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562069"},{"key":"e_1_2_2_64_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073608","article-title":"O-cnn: Octree-based convolutional neural networks for 3d shape analysis","volume":"36","author":"Wang Peng-Shuai","year":"2017","unstructured":"Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong. 2017. O-cnn: Octree-based convolutional neural networks for 3d shape analysis. ACM Trans. Graph. 36, 4 (2017), 1--11.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_65_1","volume-title":"Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations. arXiv preprint arXiv:2205.02825","author":"Liu Yang","year":"2022","unstructured":"Peng-ShuaiWang, Yang Liu, and Xin Tong. 2022. Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations. arXiv preprint arXiv:2205.02825 (2022)."},{"key":"e_1_2_2_66_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3272127.3275050","article-title":"Adaptive O-CNN: A patch-based deep representation of 3D shapes","volume":"37","author":"Wang Peng-Shuai","year":"2018","unstructured":"Peng-Shuai Wang, Chun-Yu Sun, Yang Liu, and Xin Tong. 2018. Adaptive O-CNN: A patch-based deep representation of 3D shapes. ACM Trans. Graph. 37, 6 (2018), 1--11.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_67_1","volume-title":"Neural Fields as Learnable Kernels for 3D Reconstruction. arXiv preprint arXiv:2111.13674","author":"Williams Francis","year":"2021","unstructured":"Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler, and Or Litany. 2021a. Neural Fields as Learnable Kernels for 3D Reconstruction. arXiv preprint arXiv:2111.13674 (2021)."},{"key":"e_1_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01037"},{"key":"e_1_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00982"},{"key":"e_1_2_2_70_1","volume-title":"GIFS: Neural Implicit Function for General Shape Representation. arXiv preprint arXiv:2204.07126","author":"Ye Jianglong","year":"2022","unstructured":"Jianglong Ye, Yuntao Chen, Naiyan Wang, and Xiaolong Wang. 2022. GIFS: Neural Implicit Function for General Shape Representation. arXiv preprint arXiv:2204.07126 (2022)."},{"key":"e_1_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.5555\/1648359.1648372"},{"key":"e_1_2_2_72_1","volume-title":"Thingi10k: A dataset of 10,000 3d-printing models. arXiv preprint arXiv:1605.04797","author":"Zhou Qingnan","year":"2016","unstructured":"Qingnan Zhou and Alec Jacobson. 2016. Thingi10k: A dataset of 10,000 3d-printing models. arXiv preprint arXiv:1605.04797 (2016)."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555457","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:11Z","timestamp":1750182551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":72,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1145\/3550454.3555457"],"URL":"https:\/\/doi.org\/10.1145\/3550454.3555457","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2022-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}