{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:17:46Z","timestamp":1783106266968,"version":"3.54.6"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"The Fundamental Research Funds for the Central Universities","award":["WK9100000063"],"award-info":[{"award-number":["WK9100000063"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,8,1]]},"abstract":"<jats:p>Multi-view mesh reconstruction has long been a challenging problem in graphics and computer vision. In contrast to recent volumetric rendering methods that generate meshes through post-processing, we propose an end-to-end mesh optimization approach called IMLS-Splatting. Our method leverages the sparsity and flexibility of point clouds to efficiently represent the underlying surface. To achieve this, we introduce a splatting-based differentiable Implicit Moving-Least Squares (IMLS) algorithm that enables the fast conversion of point clouds into SDFs and texture fields, optimizing both mesh reconstruction and rasterization. Additionally, the IMLS representation ensures that the reconstructed SDF and mesh maintain continuity and smoothness without the need for extra regularization. With this efficient pipeline, our method enables the reconstruction of highly detailed meshes in approximately 11 minutes, supporting high-quality rendering and achieving state-of-the-art reconstruction performance. Our code is available at https:\/\/github.com\/SilenKZYoung\/IMLS-Splatting.<\/jats:p>","DOI":"10.1145\/3731210","type":"journal-article","created":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T04:02:22Z","timestamp":1753588942000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["IMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point Representation"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3248-769X","authenticated-orcid":false,"given":"Kaizhi","family":"Yang","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8320-1619","authenticated-orcid":false,"given":"Liu","family":"Dai","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2882-2383","authenticated-orcid":false,"given":"Isabella","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5795-8469","authenticated-orcid":false,"given":"Xiaoshuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hillbot Inc., San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-5566","authenticated-orcid":false,"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-7018","authenticated-orcid":false,"given":"Xuejin","family":"Chen","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8487-8018","authenticated-orcid":false,"given":"Zexiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hillbot Inc., San Jose, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1796-2682","authenticated-orcid":false,"given":"Hao","family":"Su","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, USA"},{"name":"Hillbot Inc., San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459148"},{"key":"e_1_2_2_2_1","volume-title":"Neural Point-Based Graphics. In The European Conference on Computer Vision. 696\u2013712","author":"Aliev Kara-Ali","year":"2020","unstructured":"Kara-Ali Aliev, Artem Sevastopolsky, Maria Kolos, Dmitry Ulyanov, and Victor Lempitsky. 2020. Neural Point-Based Graphics. In The European Conference on Computer Vision. 696\u2013712."},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_2_2_4_1","volume-title":"TensoRF: Tensorial Radiance Fields. In The European Conference on Computer Vision. 333\u2013350","author":"Chen Anpei","year":"2023","unstructured":"Anpei Chen, Zexiang Xu, Andreas Geiger, Jingyi Yu, and Hao Su. 2023b. TensoRF: Tensorial Radiance Fields. In The European Conference on Computer Vision. 333\u2013350."},{"key":"e_1_2_2_5_1","unstructured":"Hanlin Chen Chen Li and Gim Hee Lee. 2023a. NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance. In arXiv preprint arXiv:2312.00846."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"e_1_2_2_7_1","volume-title":"Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4232\u20134241","author":"Han Kang","year":"2023","unstructured":"Kang Han and Wei Xiang. 2023. Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4232\u20134241."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1661"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"e_1_2_2_11_1","volume-title":"TensoIR: Tensorial Inverse Rendering. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 165\u2013174","author":"Jin Haian","year":"2023","unstructured":"Haian Jin, Isabella Liu, Peijia Xu, Xiaoshuai Zhang, Songfang Han, Sai Bi, Xiaowei Zhou, Zexiang Xu, and Hao Su. 2023. TensoIR: Tensorial Inverse Rendering. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 165\u2013174."},{"key":"e_1_2_2_12_1","volume-title":"The Eurographics Symposium on Geometry Processing.","author":"Kazhdan Michael","year":"2006","unstructured":"Michael Kazhdan, Matthew Bolitho, and Hugues Hoppe. 2006. Poisson surface reconstruction. In The Eurographics Symposium on Geometry Processing."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1361192.1361195"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14339"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_2_2_17_1","volume-title":"Pulsar: Efficient Sphere-Based Neural Rendering. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1440\u20131449","author":"Lassner Christoph","year":"2021","unstructured":"Christoph Lassner and Michael Zollhofer. 2021. Pulsar: Efficient Sphere-Based Neural Rendering. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1440\u20131449."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_8"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02052"},{"key":"e_1_2_2_20_1","unstructured":"Kunyi Li Michael Niemeyer Zeyu Chen Nassir Navab and Federico Tombari. 2024. MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction. In arXiv preprint arXiv:2411.16898."},{"key":"e_1_2_2_21_1","volume-title":"Neuralangelo: High-Fidelity Neural Surface Reconstruction. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8456\u20138465","author":"Li Zhaoshuo","year":"2023","unstructured":"Zhaoshuo Li, Thomas M\u00fcller, Alex Evans, Russell H. Taylor, Mathias Unberath, Ming-Yu Liu, and Chen-Hsuan Lin. 2023a. Neuralangelo: High-Fidelity Neural Surface Reconstruction. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8456\u20138465."},{"key":"e_1_2_2_22_1","volume-title":"DynIBaR: Neural Dynamic Image-Based Rendering. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4273\u20134284","author":"Li Zhengqi","year":"2023","unstructured":"Zhengqi Li, Qianqian Wang, Forrester Cole, Richard Tucker, and Noah Snavely. 2023b. DynIBaR: Neural Dynamic Image-Based Rendering. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4273\u20134284."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00183"},{"key":"e_1_2_2_24_1","volume-title":"SIGGRAPH Conference Papers.","author":"William","unstructured":"William E. Lorensen and Harvey E. Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm. In SIGGRAPH Conference Papers."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14344"},{"key":"e_1_2_2_26_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. In arXiv preprint arXiv:2404.00409."},{"key":"e_1_2_2_27_1","volume-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques. 545\u2013546","author":"Duane","unstructured":"Duane G. Merrill and Andrew S. Grimshaw. 2010. Revisiting sorting for GPGPU stream architectures. In Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques. 545\u2013546."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00810"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00985"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"e_1_2_2_33_1","volume-title":"UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction. In The IEEE\/CVF International Conference on Computer Vision. 5589\u20135599","author":"Oechsle Michael","year":"2021","unstructured":"Michael Oechsle, Songyou Peng, and Andreas Geiger. 2021. UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction. In The IEEE\/CVF International Conference on Computer Vision. 5589\u20135599."},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"e_1_2_2_35_1","volume-title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10318\u201310327","author":"Pumarola Albert","year":"2021","unstructured":"Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. 2021. D-NeRF: Neural Radiance Fields for Dynamic Scenes. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10318\u201310327."},{"key":"e_1_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Kerui Ren Lihan Jiang Tao Lu Mulin Yu Linning Xu Zhangkai Ni and Bo Dai. 2024. Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians. In arXiv preprint arXiv:2403.17898.","DOI":"10.1109\/TPAMI.2025.3568201"},{"key":"e_1_2_2_37_1","first-page":"6087","article-title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","volume":"34","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, Vol. 34. 6087\u20136101.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592430"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141964"},{"key":"e_1_2_2_40_1","volume-title":"The Annual Symposium on Computational Geometry.","author":"Su Peter","unstructured":"Peter Su and Robert L. Scot Drysdale. 1995. A comparison of sequential Delaunay triangulation algorithms. In The Annual Symposium on Computational Geometry."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01654"},{"key":"e_1_2_2_42_1","volume-title":"Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5459\u20135469","author":"Sun Cheng","year":"2022","unstructured":"Cheng Sun, Min Sun, and Hwann-Tzong Chen. 2022. Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5459\u20135469."},{"key":"e_1_2_2_43_1","volume-title":"Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5491\u20135500","author":"Verbin Dor","unstructured":"Dor Verbin, Peter Hedman, Ben Mildenhall, Todd Zickler, Jonathan T. Barron, and Pratul P. Srinivasan. 2022. Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5491\u20135500."},{"key":"e_1_2_2_44_1","volume-title":"Explicit Neural Surfaces: Learning Continuous Geometry with Deformation Fields. In Advances in Neural Information Processing Systems Workshop.","author":"Walker Thomas","year":"2023","unstructured":"Thomas Walker, Octave Mariotti, Amir Vaxman, and Hakan Bilen. 2023. Explicit Neural Surfaces: Learning Continuous Geometry with Deformation Fields. In Advances in Neural Information Processing Systems Workshop."},{"key":"e_1_2_2_45_1","unstructured":"Fangjinhua Wang Marie-Julie Rakotosaona Michael Niemeyer Richard Szeliski Marc Pollefeys and Federico Tombari. 2024a. UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections. In Advances in Neural Information Processing Systems."},{"key":"e_1_2_2_46_1","first-page":"27171","article-title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","volume":"34","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, Vol. 34. 27171\u201327183.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_47_1","first-page":"1966","article-title":"HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details","volume":"35","author":"Wang Yiqun","year":"2022","unstructured":"Yiqun Wang, Ivan Skorokhodov, and Peter Wonka. 2022. HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details. In Advances in Neural Information Processing Systems, Vol. 35. 1966\u20131978.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_48_1","volume-title":"PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12598\u201312607","author":"Wang Yiqun","year":"2023","unstructured":"Yiqun Wang, Ivan Skorokhodov, and Peter Wonka. 2023. PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12598\u201312607."},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3284233"},{"key":"e_1_2_2_50_1","unstructured":"Xinyue Wei Fanbo Xiang Sai Bi Anpei Chen Kalyan Sunkavalli Zexiang Xu and Hao Su. 2023. NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support. In arXiv preprint arXiv:2305.17134."},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658226"},{"key":"e_1_2_2_53_1","volume-title":"Multi-View Mesh Reconstruction With Neural Deferred Shading. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6187\u20136197","author":"Worchel Markus","year":"2022","unstructured":"Markus Worchel, Rodrigo Diaz, Weiwen Hu, Oliver Schreer, Ingo Feldmann, and Peter Eisert. 2022. Multi-View Mesh Reconstruction With Neural Deferred Shading. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6187\u20136197."},{"key":"e_1_2_2_54_1","volume-title":"Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction. In The International Conference on Learning Representations.","author":"Wu Tong","year":"2023","unstructured":"Tong Wu, Jiaqi Wang, Xingang Pan, Xudong Xu, Christian Theobalt, Ziwei Liu, and Dahua Lin. 2023. Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction. In The International Conference on Learning Representations."},{"key":"e_1_2_2_55_1","volume-title":"Point-NeRF: Point-Based Neural Radiance Fields. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5438\u20135448","author":"Xu Qiangeng","year":"2022","unstructured":"Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, and Ulrich Neumann. 2022. Point-NeRF: Point-Based Neural Radiance Fields. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5438\u20135448."},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01977"},{"key":"e_1_2_2_57_1","unstructured":"Lior Yariv Jiatao Gu Yoni Kasten and Yaron Lipman. 2021. Volume rendering of neural implicit surfaces. In Advances in Neural Information Processing Systems."},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356513"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"e_1_2_2_60_1","volume-title":"Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes. ACM Transactions on Graphics","author":"Yu Zehao","year":"2024","unstructured":"Zehao Yu, Torsten Sattler, and Andreas Geiger. 2024b. Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes. ACM Transactions on Graphics (2024)."},{"key":"e_1_2_2_61_1","unstructured":"Baowen Zhang Chuan Fang Rakesh Shrestha Yixun Liang Xiaoxiao Long and Ping Tan. 2024. RaDe-GS: Rasterizing Depth in Gaussian Splatting. In arXiv preprint arXiv:2406.01467."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:51:55Z","timestamp":1774633915000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":61,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8,1]]}},"alternative-id":["10.1145\/3731210"],"URL":"https:\/\/doi.org\/10.1145\/3731210","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}