{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T05:25:13Z","timestamp":1780723513078,"version":"3.54.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hong Kong Research Grant Council","award":["ECS 27209621"],"award-info":[{"award-number":["ECS 27209621"]}]},{"name":"Hong Kong Research Grant Council","award":["GRF 17202422"],"award-info":[{"award-number":["GRF 17202422"]}]},{"name":"Hong Kong Research Grant Council","award":["GRF 17212923"],"award-info":[{"award-number":["GRF 17212923"]}]},{"name":"Hong Kong Research Grant Council","award":["T45-701\/22-R"],"award-info":[{"award-number":["T45-701\/22-R"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2024,12,19]]},"abstract":"<jats:p>In this paper, we present an implicit surface reconstruction method with 3D Gaussian Splatting (3DGS), namely 3DGSR, that allows for accurate 3D reconstruction with intricate details while inheriting the high efficiency and rendering quality of 3DGS. The key insight is to incorporate an implicit signed distance field (SDF) within 3D Gaussians for surface modeling, and to enable the alignment and joint optimization of both SDF and 3D Gaussians. To achieve this, we design coupling strategies that align and associate the SDF with 3D Gaussians, allowing for unified optimization and enforcing surface constraints on the 3D Gaussians. With alignment, optimizing the 3D Gaussians provides supervisory signals for SDF learning, enabling the reconstruction of intricate details. However, this only offers sparse supervisory signals to the SDF at locations occupied by Gaussians, which is insufficient for learning a continuous SDF. Then, to address this limitation, we incorporate volumetric rendering and align the rendered geometric attributes (depth, normal) with that derived from 3DGS. In sum, these two designs allow SDF and 3DGS to be aligned, jointly optimized, and mutually boosted. Our extensive experimental results demonstrate that our 3DGSR enables high-quality 3D surface reconstruction while preserving the efficiency and rendering quality of 3DGS. Besides, our method competes favorably with leading surface reconstruction techniques while offering a more efficient learning process and much better rendering qualities.<\/jats:p>","DOI":"10.1145\/3687952","type":"journal-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T15:46:04Z","timestamp":1732031164000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":60,"title":["3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1318-4905","authenticated-orcid":false,"given":"Xiaoyang","family":"Lyu","sequence":"first","affiliation":[{"name":"The University of Hong Kong (HKU), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6370-1603","authenticated-orcid":false,"given":"Yang-Tian","family":"Sun","sequence":"additional","affiliation":[{"name":"The University of Hong Kong (HKU), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-8280","authenticated-orcid":false,"given":"Yi-Hua","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong (HKU), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5565-4541","authenticated-orcid":false,"given":"Xiuzhe","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong (HKU), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-4704","authenticated-orcid":false,"given":"Ziyi","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong (HKU), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3372-8703","authenticated-orcid":false,"given":"Yilun","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shang Hai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-9319","authenticated-orcid":false,"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shang Hai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-1626","authenticated-orcid":false,"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong (HKU), Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_2_1_2_1","volume-title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields. ICCV","author":"Barron Jonathan T.","year":"2023","unstructured":"Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, and Peter Hedman. 2023. Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields. ICCV (2023)."},{"key":"e_1_2_1_3_1","volume-title":"NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance. arXiv preprint arXiv:2312.00846","author":"Chen Hanlin","year":"2023","unstructured":"Hanlin Chen, Chen Li, and Gim Hee Lee. 2023. NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance. arXiv preprint arXiv:2312.00846 (2023)."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657441"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00616"},{"key":"e_1_2_1_6_1","volume-title":"Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction. arXiv preprint arXiv:2312.01196","author":"Das Devikalyan","year":"2023","unstructured":"Devikalyan Das, Christopher Wewer, Raza Yunus, Eddy Ilg, and Jan Eric Lenssen. 2023. Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction. arXiv preprint arXiv:2312.01196 (2023)."},{"key":"e_1_2_1_7_1","volume-title":"Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing. arXiv preprint arXiv:2311.16043","author":"Gao Jian","year":"2023","unstructured":"Jian Gao, Chun Gu, Youtian Lin, Hao Zhu, Xun Cao, Li Zhang, and Yao Yao. 2023. Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing. arXiv preprint arXiv:2311.16043 (2023)."},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of Machine Learning and Systems","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 Proceedings of Machine Learning and Systems 2020. 3569--3579."},{"key":"e_1_2_1_9_1","volume-title":"SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. arXiv preprint arXiv:2311.12775","author":"Gu\u00e9don Antoine","year":"2023","unstructured":"Antoine Gu\u00e9don and Vincent Lepetit. 2023. SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. arXiv preprint arXiv:2311.12775 (2023)."},{"key":"e_1_2_1_10_1","volume-title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields. SIGGRAPH","author":"Huang Binbin","year":"2024","unstructured":"Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, and Shenghua Gao. 2024. 2D Gaussian Splatting for Geometrically Accurate Radiance Fields. SIGGRAPH (2024)."},{"key":"e_1_2_1_11_1","volume-title":"SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes. arXiv preprint arXiv:2312.14937","author":"Huang Yi-Hua","year":"2023","unstructured":"Yi-Hua Huang, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, and Xiaojuan Qi. 2023. SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes. arXiv preprint arXiv:2312.14937 (2023)."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00133"},{"key":"e_1_2_1_14_1","volume-title":"Deformable 3D Gaussian Splatting for Animatable Human Avatars. arXiv preprint arXiv:2312.15059","author":"Jung HyunJun","year":"2023","unstructured":"HyunJun Jung, Nikolas Brasch, Jifei Song, Eduardo Perez-Pellitero, Yiren Zhou, Zhihao Li, Nassir Navab, and Benjamin Busam. 2023. Deformable 3D Gaussian Splatting for Animatable Human Avatars. arXiv preprint arXiv:2312.15059 (2023)."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487237"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00427"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_2_1_19_1","volume-title":"Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis. arXiv preprint arXiv:2312.16812","author":"Li Zhan","year":"2023","unstructured":"Zhan Li, Zhang Chen, Zhong Li, and Yi Xu. 2023a. Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis. arXiv preprint arXiv:2312.16812 (2023)."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"e_1_2_1_21_1","first-page":"15651","article-title":"Neural sparse voxel fields","volume":"33","author":"Liu Lingjie","year":"2020","unstructured":"Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. 2020a. Neural sparse voxel fields. Advances in Neural Information Processing Systems 33 (2020), 15651--15663.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00209"},{"key":"e_1_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Yuan Liu Peng Wang Cheng Lin Xiaoxiao Long Jiepeng Wang Lingjie Liu Taku Komura and Wenping Wang. 2023. NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images.","DOI":"10.1145\/3592134"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323020"},{"key":"e_1_2_1_25_1","volume-title":"Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713","author":"Luiten Jonathon","year":"2023","unstructured":"Jonathon Luiten, Georgios Kopanas, Bastian Leibe, and Deva Ramanan. 2023. Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713 (2023)."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_2_1_27_1","unstructured":"Thomas M\u00fcller. 2021. tiny-cuda-nn. https:\/\/github.com\/NVlabs\/tiny-cuda-nn"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"e_1_2_1_30_1","volume-title":"DreamGaussian4D: Generative 4D Gaussian Splatting. arXiv preprint arXiv:2312.17142","author":"Ren Jiawei","year":"2023","unstructured":"Jiawei Ren, Liang Pan, Jiaxiang Tang, Chi Zhang, Ang Cao, Gang Zeng, and Ziwei Liu. 2023. DreamGaussian4D: Generative 4D Gaussian Splatting. arXiv preprint arXiv:2312.17142 (2023)."},{"key":"e_1_2_1_31_1","volume-title":"Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Sch\u00f6nberger Johannes Lutz","year":"2016","unstructured":"Johannes Lutz Sch\u00f6nberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_1_32_1","volume-title":"Scene representation networks: Continuous 3d-structure-aware neural scene representations. Advances in Neural Information Processing Systems 32","author":"Sitzmann Vincent","year":"2019","unstructured":"Vincent Sitzmann, Michael Zollh\u00f6fer, and Gordon Wetzstein. 2019. Scene representation networks: Continuous 3d-structure-aware neural scene representations. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_2_1_33_1","volume-title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. arXiv preprint arXiv:2309.16653","author":"Tang Jiaxiang","year":"2023","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2023a. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. arXiv preprint arXiv:2309.16653 (2023)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01626"},{"key":"e_1_2_1_35_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. arXiv preprint arXiv:2106.10689 (2021)."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00305"},{"key":"e_1_2_1_37_1","volume-title":"Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting. arXiv preprint arXiv:2312.04820","author":"Yang Xiaofeng","year":"2023","unstructured":"Xiaofeng Yang, Yiwen Chen, Cheng Chen, Chi Zhang, Yi Xu, Xulei Yang, Fayao Liu, and Guosheng Lin. 2023a. Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting. arXiv preprint arXiv:2312.04820 (2023)."},{"key":"e_1_2_1_38_1","volume-title":"Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101","author":"Yang Ziyi","year":"2023","unstructured":"Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, and Xiaogang Jin. 2023b. Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101 (2023)."},{"key":"e_1_2_1_39_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Yang Zeyu","year":"2024","unstructured":"Zeyu Yang, Hongye Yang, Zijie Pan, Xiatian Zhu, and Li Zhang. 2024. Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_1_40_1","first-page":"4805","article-title":"Volume rendering of neural implicit surfaces","volume":"34","author":"Yariv Lior","year":"2021","unstructured":"Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume rendering of neural implicit surfaces. Advances in Neural Information Processing Systems 34 (2021), 4805--4815.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_41_1","volume-title":"BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis. arXiv","author":"Yariv Lior","year":"2023","unstructured":"Lior Yariv, Peter Hedman, Christian Reiser, Dor Verbin, Pratul P. Srinivasan, Richard Szeliski, Jonathan T. Barron, and Ben Mildenhall. 2023. BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis. arXiv (2023)."},{"key":"e_1_2_1_42_1","first-page":"2492","article-title":"Multiview neural surface reconstruction by disentangling geometry and appearance","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. Advances in Neural Information Processing Systems 33 (2020), 2492--2502.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_43_1","volume-title":"Animatable 3d gaussians for high-fidelity synthesis of human motions. arXiv preprint arXiv:2311.13404","author":"Ye Keyang","year":"2023","unstructured":"Keyang Ye, Tianjia Shao, and Kun Zhou. 2023. Animatable 3d gaussians for high-fidelity synthesis of human motions. arXiv preprint arXiv:2311.13404 (2023)."},{"key":"e_1_2_1_44_1","volume-title":"Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529","author":"Yi Taoran","year":"2023","unstructured":"Taoran Yi, Jiemin Fang, Guanjun Wu, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Qi Tian, and Xinggang Wang. 2023. Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529 (2023)."},{"key":"e_1_2_1_45_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] https:\/\/arxiv.org\/abs\/2403.16964"},{"key":"e_1_2_1_46_1","volume-title":"Gaussian Opacity Fields: Efficient High-quality Compact Surface Reconstruction in Unbounded Scenes. arXiv:2404.10772","author":"Yu Zehao","year":"2024","unstructured":"Zehao Yu, Torsten Sattler, and Andreas Geiger. 2024b. Gaussian Opacity Fields: Efficient High-quality Compact Surface Reconstruction in Unbounded Scenes. arXiv:2404.10772 (2024)."},{"key":"e_1_2_1_47_1","volume-title":"Drivable 3d gaussian avatars. arXiv preprint arXiv:2311.08581","author":"Zielonka Wojciech","year":"2023","unstructured":"Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito, Michael Zollh\u00f6fer, Justus Thies, and Javier Romero. 2023. Drivable 3d gaussian avatars. arXiv preprint arXiv:2311.08581 (2023)."},{"key":"e_1_2_1_48_1","doi-asserted-by":"crossref","unstructured":"M. Zwicker H. Pfister J. van Baar and M. Gross. 2001. Surface Splatting. In ACM Transactions on Graphics (Proc. ACM SIGGRAPH). 371--378.","DOI":"10.1145\/383259.383300"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687952","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3687952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:57Z","timestamp":1750295397000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12,19]]}},"alternative-id":["10.1145\/3687952"],"URL":"https:\/\/doi.org\/10.1145\/3687952","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,19]]},"assertion":[{"value":"2024-11-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}