{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T22:31:57Z","timestamp":1791930717123,"version":"4.3.4"},"reference-count":54,"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"}],"funder":[{"name":"Google gift"},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["611370"],"award-info":[{"award-number":["611370"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:p>\n            We introduce\n            <jats:italic>Neural Marching Cubes<\/jats:italic>\n            , a\n            <jats:italic>data-driven<\/jats:italic>\n            approach for extracting a triangle mesh from a discretized implicit field. We base our meshing approach on Marching Cubes (MC), due to the simplicity of its input, namely a uniform grid of signed distances or occupancies, which frequently arise in surface reconstruction and from neural implicit models. However, classical MC is defined by coarse tessellation templates isolated to individual cubes. While more refined tessellations have been proposed by several MC variants, they all make heuristic assumptions, such as trilinearity, when determining the vertex positions and local mesh topologies in each cube. In principle, none of these approaches can reconstruct geometric features that reveal coherence or dependencies between nearby cubes (e.g., a\n            <jats:italic>sharp edge<\/jats:italic>\n            ), as such information is unaccounted for, resulting in poor estimates of the true underlying implicit field. To tackle these challenges, we re-cast MC from a deep learning perspective, by designing tessellation templates more apt at preserving geometric features, and learning the vertex positions and mesh topologies from training meshes, to account for\n            <jats:italic>contextual<\/jats:italic>\n            information from nearby cubes. We develop a compact per-cube parameterization to represent the output triangle mesh, while being compatible with neural processing, so that a simple 3D convolutional network can be employed for the training. We show that all topological cases in each cube that are applicable to our design can be easily derived using our representation, and the resulting tessellations can also be obtained naturally and efficiently by following a few design guidelines. In addition, our network learns local features with limited receptive fields, hence it generalizes well to new shapes and new datasets. We evaluate our neural MC approach by quantitative and qualitative comparisons to all well-known MC variants. In particular, we demonstrate the ability of our network to recover sharp features such as edges and corners, a long-standing issue of MC and its variants. Our network also reconstructs local mesh topologies more accurately than previous approaches. Code and data are available at https:\/\/github.com\/czq142857\/NMC.\n          <\/jats:p>","DOI":"10.1145\/3478513.3480518","type":"journal-article","created":{"date-parts":[[2021,12,10]],"date-time":"2021-12-10T18:28:45Z","timestamp":1639160925000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":92,"title":["Neural marching cubes"],"prefix":"10.1145","volume":"40","author":[{"given":"Zhiqin","family":"Chen","sequence":"first","affiliation":[{"name":"Simon Fraser University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,12,10]]},"reference":[{"key":"e_1_2_2_1_1","volume":"201","author":"Achlioptas Panos","unstructured":"Panos Achlioptas , Olga Diamanti , Ioannis Mitliagkas , and Leonidas J. Guibas. 201 8. Learning representations and generative models for 3D point clouds. In ICML. Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, and Leonidas J. Guibas. 2018. Learning representations and generative models for 3D point clouds. In ICML.","journal-title":"Leonidas J. Guibas."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.118"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.491"},{"key":"e_1_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Zhiqin Chen Andrea Tagliasacchi and Hao Zhang. 2020. BSP-Net: generating compact meshes via binary space partitioning. In CVPR.  Zhiqin Chen Andrea Tagliasacchi and Hao Zhang. 2020. BSP-Net: generating compact meshes via binary space partitioning. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00012"},{"key":"e_1_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Zhiqin Chen and Hao Zhang. 2019. Learning implicit fields for generative shape modeling. In CVPR.  Zhiqin Chen and Hao Zhang. 2019. Learning implicit fields for generative shape modeling. In CVPR.","DOI":"10.1109\/CVPR.2019.00609"},{"key":"e_1_2_2_7_1","unstructured":"Christopher B. Choy Danfei Xu JunYoung Gwak Kevin Chen and Silvio Savarese. 2016. 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In ECCV.  Christopher B. Choy Danfei Xu JunYoung Gwak Kevin Chen and Silvio Savarese. 2016. 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In ECCV."},{"key":"e_1_2_2_8_1","volume-title":"Reconstruction of topologically correct and adaptive trilinear isosurfaces. Computers & Graphics","author":"Cignoni Paolo","year":"2000","unstructured":"Paolo Cignoni , Fabio Ganovelli , Claudio Montani , and Roberto Scopigno . 2000. Reconstruction of topologically correct and adaptive trilinear isosurfaces. Computers & Graphics ( 2000 ). Paolo Cignoni, Fabio Ganovelli, Claudio Montani, and Roberto Scopigno. 2000. Reconstruction of topologically correct and adaptive trilinear isosurfaces. Computers & Graphics (2000)."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2013.04.004"},{"key":"e_1_2_2_10_1","unstructured":"Angela Dai and Matthias Nie\u00dfner. 2019. Scan2Mesh: from unstructured range scans to 3D meshes. In CVPR.  Angela Dai and Matthias Nie\u00dfner. 2019. Scan2Mesh: from unstructured range scans to 3D meshes. In CVPR."},{"key":"e_1_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Boyang Deng Kyle Genova Soroosh Yazdani Sofien Bouaziz Geoffrey Hinton and Andrea Tagliasacchi. 2020. Cvxnet: learnable convex decomposition. In CVPR.  Boyang Deng Kyle Genova Soroosh Yazdani Sofien Bouaziz Geoffrey Hinton and Andrea Tagliasacchi. 2020. Cvxnet: learnable convex decomposition. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00011"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-008-0224-1"},{"key":"e_1_2_2_13_1","volume-title":"An efficient method of triangulating equi-valued surfaces by using tetrahedral cells. IEICE Transactions on Information and Systems","author":"Doi Akio","year":"1991","unstructured":"Akio Doi and Akio Koide . 1991. An efficient method of triangulating equi-valued surfaces by using tetrahedral cells. IEICE Transactions on Information and Systems ( 1991 ). Akio Doi and Akio Koide. 1991. An efficient method of triangulating equi-valued surfaces by using tetrahedral cells. IEICE Transactions on Information and Systems (1991)."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/378267.378271"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.109"},{"key":"e_1_2_2_16_1","volume":"201","author":"Fan Haoqiang","unstructured":"Haoqiang Fan , Hao Su , and Leonidas J. Guibas. 201 7. A point set generation network for 3D object reconstruction from a single image. In CVPR. Haoqiang Fan, Hao Su, and Leonidas J. Guibas. 2017. A point set generation network for 3D object reconstruction from a single image. In CVPR.","journal-title":"Leonidas J. Guibas."},{"key":"e_1_2_2_17_1","volume-title":"Alec Jacobson, Morgan McGuire, and Sanja Fidler.","author":"Gao Jun","year":"2020","unstructured":"Jun Gao , Wenzheng Chen , Tommy Xiang , Clement Fuji Tsang , Alec Jacobson, Morgan McGuire, and Sanja Fidler. 2020 . Learning deformable tetrahedral meshes for 3D reconstruction. In NeurIPS. Jun Gao, Wenzheng Chen, Tommy Xiang, Clement Fuji Tsang, Alec Jacobson, Morgan McGuire, and Sanja Fidler. 2020. Learning deformable tetrahedral meshes for 3D reconstruction. In NeurIPS."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356488"},{"key":"e_1_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Thibault Groueix Matthew Fisher Vladimir G. Kim Bryan Russell and Mathieu Aubry. 2018. AtlasNet: a papier-m\u00e2ch\u00e9 approach to learning 3D surface generation. In CVPR.  Thibault Groueix Matthew Fisher Vladimir G. Kim Bryan Russell and Mathieu Aubry. 2018. AtlasNet: a papier-m\u00e2ch\u00e9 approach to learning 3D surface generation. In CVPR.","DOI":"10.1109\/CVPR.2018.00030"},{"key":"e_1_2_2_20_1","unstructured":"Christian H\u00e4ne Shubham Tulsiani and Jitendra Malik. 2017. Hierarchical surface prediction for 3D object reconstruction. In 3DV.  Christian H\u00e4ne Shubham Tulsiani and Jitendra Malik. 2017. Hierarchical surface prediction for 3D object reconstruction. In 3DV."},{"key":"e_1_2_2_21_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566586"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383265"},{"key":"e_1_2_2_24_1","unstructured":"Sebastian Koch Albert Matveev Zhongshi Jiang Francis Williams Alexey Artemov Evgeny Burnaev Marc Alexa Denis Zorin and Daniele Panozzo. 2019. ABC: a big CAD model dataset for geometric deep learning. In CVPR.  Sebastian Koch Albert Matveev Zhongshi Jiang Francis Williams Alexey Artemov Evgeny Burnaev Marc Alexa Denis Zorin and Daniele Panozzo. 2019. ABC: a big CAD model dataset for geometric deep learning. In CVPR."},{"key":"e_1_2_2_25_1","unstructured":"Jiabao Lei and Kui Jia. 2020. Analytic marching: an analytic meshing solution from deep implicit surface networks. In ICML.  Jiabao Lei and Kui Jia. 2020. Analytic marching: an analytic meshing solution from deep implicit surface networks. In ICML."},{"key":"e_1_2_2_26_1","volume-title":"Ant\u00f4nio Wilson Vieira, and Geovan Tavares","author":"Lewiner Thomas","year":"2003","unstructured":"Thomas Lewiner , H\u00e9lio Lopes , Ant\u00f4nio Wilson Vieira, and Geovan Tavares . 2003 . Efficient implementation of marching cubes' cases with topological guarantees. Journal of Graphics Tools ( 2003). Thomas Lewiner, H\u00e9lio Lopes, Ant\u00f4nio Wilson Vieira, and Geovan Tavares. 2003. Efficient implementation of marching cubes' cases with topological guarantees. Journal of Graphics Tools (2003)."},{"key":"e_1_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Yiyi Liao Simon Donne and Andreas Geiger. 2018. Deep marching cubes: learning explicit surface representations. In CVPR.  Yiyi Liao Simon Donne and Andreas Geiger. 2018. Deep marching cubes: learning explicit surface representations. In CVPR.","DOI":"10.1109\/CVPR.2018.00308"},{"key":"e_1_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Cheng Lin Changjian Li Yuan Liu Nenglun Chen Yi-King Choi and Wenping Wang. 2021. Point2Skeleton: Learning Skeletal Representations from Point Clouds. In CVPR.  Cheng Lin Changjian Li Yuan Liu Nenglun Chen Yi-King Choi and Wenping Wang. 2021. Point2Skeleton: Learning Skeletal Representations from Point Clouds. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00426"},{"key":"e_1_2_2_29_1","volume-title":"Neural subdivision. ACM Transactions on Graphics","author":"Derek Liu Hsueh-Ti","year":"2020","unstructured":"Hsueh-Ti Derek Liu , Vladimir G. Kim , Siddhartha Chaudhuri , Noam Aigerman , and Alec Jacobson . 2020. Neural subdivision. ACM Transactions on Graphics ( 2020 ). Hsueh-Ti Derek Liu, Vladimir G. Kim, Siddhartha Chaudhuri, Noam Aigerman, and Alec Jacobson. 2020. Neural subdivision. ACM Transactions on Graphics (2020)."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2003.1175094"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/951087.951140"},{"key":"e_1_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Lars Mescheder Michael Oechsle Michael Niemeyer Sebastian Nowozin and Andreas Geiger. 2019. Occupancy networks: learning 3D reconstruction in function space. In CVPR.  Lars Mescheder Michael Oechsle Michael Niemeyer Sebastian Nowozin and Andreas Geiger. 2019. Occupancy networks: learning 3D reconstruction in function space. In CVPR.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2003.1207437"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/949607.949621"},{"key":"e_1_2_2_36_1","unstructured":"Jeong Joon Park Peter Florence Julian Straub Richard Newcombe and Steven Lovegrove. 2019. DeepSDF: Learning continuous signed distance functions for shape representation. In CVPR.  Jeong Joon Park Peter Florence Julian Straub Richard Newcombe and Steven Lovegrove. 2019. DeepSDF: Learning continuous signed distance functions for shape representation. In CVPR."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"e_1_2_2_38_1","volume-title":"MeshSDF: differentiable iso-surface extraction. NeurIPS","author":"Remelli Edoardo","year":"2020","unstructured":"Edoardo Remelli , Artem Lukoianov , Stephan R. Richter , Beno\u00eet Guillard , Timur Bagautdinov , Pierre Baque , and Pascal Fua . 2020. MeshSDF: differentiable iso-surface extraction. NeurIPS ( 2020 ). Edoardo Remelli, Artem Lukoianov, Stephan R. Richter, Beno\u00eet Guillard, Timur Bagautdinov, Pierre Baque, and Pascal Fua. 2020. MeshSDF: differentiable iso-surface extraction. NeurIPS (2020)."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.1012"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/1025128.1026029"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.149"},{"key":"e_1_2_2_42_1","unstructured":"Vincent Sitzmann Julien N.P. Martel Alexander W. Bergman David B. Lindell and Gordon Wetzstein. 2020. Implicit Neural Representations with Periodic Activation Functions. In NeurIPS.  Vincent Sitzmann Julien N.P. Martel Alexander W. Bergman David B. Lindell and Gordon Wetzstein. 2020. Implicit Neural Representations with Periodic Activation Functions. In NeurIPS."},{"key":"e_1_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Maxim Tatarchenko Stephan R Richter Ren\u00e9 Ranftl Zhuwen Li Vladlen Koltun and Thomas Brox. 2019. What do single-view 3d reconstruction networks learn?. In CVPR.  Maxim Tatarchenko Stephan R Richter Ren\u00e9 Ranftl Zhuwen Li Vladlen Koltun and Thomas Brox. 2019. What do single-view 3d reconstruction networks learn?. In CVPR.","DOI":"10.1109\/CVPR.2019.00352"},{"key":"e_1_2_2_44_1","volume-title":"scikit-image: image processing in Python. PeerJ","author":"der Walt Stefan Van","year":"2014","unstructured":"Stefan Van der Walt , Johannes L Sch\u00f6nberger , Juan Nunez-Iglesias , Fran\u00e7ois Boulogne , Joshua D Warner , Neil Yager , Emmanuelle Gouillart , and Tony Yu. 2014. scikit-image: image processing in Python. PeerJ ( 2014 ). Stefan Van der Walt, Johannes L Sch\u00f6nberger, Juan Nunez-Iglesias, Fran\u00e7ois Boulogne, Joshua D Warner, Neil Yager, Emmanuelle Gouillart, and Tony Yu. 2014. scikit-image: image processing in Python. PeerJ (2014)."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/195826.195828"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2003.1250360"},{"key":"e_1_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Nanyang Wang Yinda Zhang Zhuwen Li Yanwei Fu Wei Liu and Yu-Gang Jiang. 2018. Pixel2Mesh: generating 3D mesh models from single RGB images. In ECCV.  Nanyang Wang Yinda Zhang Zhuwen Li Yanwei Fu Wei Liu and Yu-Gang Jiang. 2018. Pixel2Mesh: generating 3D mesh models from single RGB images. In ECCV.","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980232"},{"key":"e_1_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Weiyue Wang Duygu Ceylan Radomir Mech and Ulrich Neumann. 2019. 3DN: 3D deformation network. In CVPR.  Weiyue Wang Duygu Ceylan Radomir Mech and Ulrich Neumann. 2019. 3DN: 3D deformation network. In CVPR.","DOI":"10.1109\/CVPR.2019.00113"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157106"},{"key":"e_1_2_2_51_1","volume-title":"Data structure for soft objects. The Visual Computer","author":"Wyvill Geoff","year":"1986","unstructured":"Geoff Wyvill , Craig McPheeters , and Brian Wyvill . 1986. Data structure for soft objects. The Visual Computer ( 1986 ). Geoff Wyvill, Craig McPheeters, and Brian Wyvill. 1986. Data structure for soft objects. The Visual Computer (1986)."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356494"},{"key":"e_1_2_2_53_1","unstructured":"Lequan Yu Xianzhi Li Chi-Wing Fu Daniel Cohen-Or and Pheng-Ann Heng. 2018. PU-Net: Point Cloud Upsampling Network. In CVPR.  Lequan Yu Xianzhi Li Chi-Wing Fu Daniel Cohen-Or and Pheng-Ann Heng. 2018. PU-Net: Point Cloud Upsampling Network. In CVPR."},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2004.27"},{"key":"e_1_2_2_55_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 ). 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\/3478513.3480518","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3478513.3480518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:49Z","timestamp":1750191109000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478513.3480518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1145\/3478513.3480518"],"URL":"https:\/\/doi.org\/10.1145\/3478513.3480518","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"}}]}}