{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T12:30:02Z","timestamp":1766147402495,"version":"3.48.0"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"Innovation and Technology Commission of the HKSAR Government","award":["T45-205\/21-N"],"award-info":[{"award-number":["T45-205\/21-N"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Piecewise parametric surfaces have long been established as prevalent geometric representations; however, they often require surface refinement or sophisticated quadrangulation to accurately represent complex geometries. Geometric deep learning has shown that neural networks can provide greater representational power than conventional methods. Nevertheless, approaches using a single parametric surface for shape fitting struggle to capture fine-grained geometric details, while multi-patch methods fail to ensure seamless connections between adjacent patches.<\/jats:p>\n                  <jats:p>\n                    We present\n                    <jats:italic toggle=\"yes\">Neural Piecewise Parametric Surfaces<\/jats:italic>\n                    (\n                    <jats:italic toggle=\"yes\">NeuPPS<\/jats:italic>\n                    ), the\n                    <jats:italic toggle=\"yes\">first<\/jats:italic>\n                    piecewise neural surface representation that allows for coarse patch layouts composed of\n                    <jats:italic toggle=\"yes\">\n                      arbitrary\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      -sided surface patches\n                    <\/jats:italic>\n                    to model complex surface geometries with high precision, offering enhanced\n                    <jats:italic toggle=\"yes\">flexibility<\/jats:italic>\n                    compared with traditional parametric surfaces. This new surface representation guarantees, by construction, the continuity between adjacent patches, a property that other neural patch-based approaches cannot ensure. Two novel components are introduced: a learnable feature complex and a continuous mapping function approximated by multi-layer perceptrons (MLPs). We apply the proposed\n                    <jats:italic toggle=\"yes\">NeuPPS<\/jats:italic>\n                    to surface fitting and shape space learning tasks. Extensive experiments demonstrate the advantages of\n                    <jats:italic toggle=\"yes\">NeuPPS<\/jats:italic>\n                    over traditional parametric representations and existing patch-based learning approaches.\n                  <\/jats:p>","DOI":"10.1145\/3771546","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T11:20:42Z","timestamp":1761736842000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NeuPPS: Neural Piecewise Parametric Surfaces"],"prefix":"10.1145","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3284-4019","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"first","affiliation":[{"name":"The University of Hong Kong","place":["Hong Kong, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7282-0476","authenticated-orcid":false,"given":"Yongqing","family":"Liang","sequence":"additional","affiliation":[{"name":"Texas A&M University System","place":["College Station, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-9489","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Texas A&M University","place":["College Station, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4259-2863","authenticated-orcid":false,"given":"Congyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong","place":["Hong Kong, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5233-3910","authenticated-orcid":false,"given":"Guying","family":"Lin","sequence":"additional","affiliation":[{"name":"Computer Science, The University of Hong Kong","place":["Hong Kong, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3335-6623","authenticated-orcid":false,"given":"Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology","place":["Macau, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9251-3716","authenticated-orcid":false,"given":"Alla","family":"Sheffer","sequence":"additional","affiliation":[{"name":"Computer Science, University of British Columbia","place":["Vancouver, Canada"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0988-1452","authenticated-orcid":false,"given":"Scott","family":"Schaefer","sequence":"additional","affiliation":[{"name":"Texas A&M University","place":["College Station, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4829-9975","authenticated-orcid":false,"given":"John","family":"Keyser","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Texas A&M Univeristy","place":["College Station, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2284-3952","authenticated-orcid":false,"given":"Wenping","family":"Wang","sequence":"additional","affiliation":[{"name":"Texas A&M University","place":["College Station, United States"]}]}],"member":"320","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"e_1_3_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1449715.1449740"},{"key":"e_1_3_1_3_1","first-page":"4716","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Bedna\u0159\u00edk Jan","year":"2020","unstructured":"Jan Bedna\u0159\u00edk, Shaifali Parashar, Erhan Gundogdu, Mathieu Salzmann, and Pascal Fua. 2020. Shape reconstruction by learning differentiable surface representations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4716\u20134725."},{"key":"e_1_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618379"},{"key":"e_1_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13153"},{"key":"e_1_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591531"},{"key":"e_1_3_1_7_1","unstructured":"Julian Chibane Mohamad Aymen Mir and Gerard Pons-Moll. 2020. Neural unsigned distance fields for implicit function learning. In Advances in Neural Information Processing Systems 33 26 (2020) 21638\u201321652."},{"key":"e_1_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186562.1015817"},{"key":"e_1_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01015"},{"key":"e_1_3_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00069"},{"key":"e_1_3_1_11_1","unstructured":"Theo Deprelle Thibault Groueix Noam Aigerman Vladimir G Kim and Mathieu Aubry. 2022. Learning joint surface atlases. arXiv:2206.06273. Retrieved from https:\/\/arxiv.org\/abs\/2206.06273"},{"key":"e_1_3_1_12_1","article-title":"Learning elementary structures for 3d shape generation and matching","volume":"32","author":"Deprelle Theo","year":"2019","unstructured":"Theo Deprelle, Thibault Groueix, Matthew Fisher, Vladimir Kim, Bryan Russell, and Mathieu Aubry. 2019. Learning elementary structures for 3d shape generation and matching. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_13_1","first-page":"1","volume-title":"ACM SIGGRAPH 2024 Conference Papers","author":"Sivaram Venkataram Edavamadathil","year":"2024","unstructured":"Venkataram Edavamadathil Sivaram, Tzu-Mao Li, and Ravi Ramamoorthi. 2024. Neural geometry fields for meshes. In ACM SIGGRAPH 2024 Conference Papers. 1\u201311."},{"key":"e_1_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8396(03)00002-5"},{"key":"e_1_3_1_15_1","first-page":"1107","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Gadelha Matheus","year":"2021","unstructured":"Matheus Gadelha, Rui Wang, and Subhransu Maji. 2021. Deep manifold prior. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1107\u20131116."},{"key":"e_1_3_1_16_1","volume-title":"Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Gao Daiheng","year":"2022","unstructured":"Daiheng Gao, Yuliang Xiu, Kailin Li, Lixin Yang, Feng Wang, Peng Zhang, Bang Zhang, Cewu Lu, and Ping Tan. 2022. DART: Articulated hand model with diverse accessories and rich textures. In Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_1_17_1","first-page":"3789","volume-title":"International Conference on Machine Learning","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 International Conference on Machine Learning. PMLR, 3789\u20133799."},{"key":"e_1_3_1_18_1","first-page":"230","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Groueix Thibault","year":"2018","unstructured":"Thibault Groueix, Matthew Fisher, Vladimir G Kim, Bryan C Russell, and Mathieu Aubry. 2018b. 3d-coded: 3d correspondences by deep deformation. In Proceedings of the European Conference on Computer Vision (ECCV). 230\u2013246."},{"key":"e_1_3_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00030"},{"key":"e_1_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530078"},{"key":"e_1_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555502"},{"key":"e_1_3_1_22_1","first-page":"1","volume-title":"ACM SIGGRAPH 2010 Papers","author":"Kalogerakis Evangelos","year":"2010","unstructured":"Evangelos Kalogerakis, Aaron Hertzmann, and Karan Singh. 2010. Learning 3D mesh segmentation and labeling. In ACM SIGGRAPH 2010 Papers. 1\u201312."},{"key":"e_1_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2020.101908"},{"key":"e_1_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487237"},{"key":"e_1_3_1_25_1","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"e_1_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2008.200"},{"issue":"6","key":"e_1_3_1_28_1","first-page":"2430","article-title":"Seg-mat: 3d shape segmentation using medial axis transform","volume":"28","author":"Lin Cheng","year":"2020","unstructured":"Cheng Lin, Lingjie Liu, Changjian Li, Leif Kobbelt, Bin Wang, Shiqing Xin, and Wenping Wang. 2020. Seg-mat: 3d shape segmentation using medial axis transform. IEEE Transactions on Visualization and Computer Graphics 28, 6 (2020), 2430\u20132444.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657482"},{"key":"e_1_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201331"},{"key":"e_1_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392472"},{"key":"e_1_3_1_32_1","first-page":"465","volume-title":"European Conference on Computer Vision","author":"Low Weng Fei","year":"2022","unstructured":"Weng Fei Low and Gim Hee Lee. 2022. Minimal neural atlas: Parameterizing complex surfaces with minimal charts and distortion. In European Conference on Computer Vision. Springer, 465\u2013481."},{"key":"e_1_3_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459785"},{"key":"e_1_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00461"},{"key":"e_1_3_1_35_1","unstructured":"Thomas M\u00fcller. 2021. tiny-cuda-nn. (42021). Retrieved from https:\/\/github.com\/NVlabs\/tiny-cuda-nn"},{"key":"e_1_3_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766990"},{"key":"e_1_3_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_1_39_1","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32. H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 8024\u20138035. Retrieved from http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_1_40_1","unstructured":"Charles Ruizhongtai Qi Li Yi Hao Su and Leonidas J. Guibas. 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems 30 (23017) 5105\u20135114."},{"key":"e_1_3_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.2983621"},{"key":"e_1_3_1_42_1","unstructured":"P. V. Sander Z. J. Wood S. J. Gortler J. Snyder and H. Hoppe. 2003. Multi-chart geometry images. In Proceedings of the 2003 Eurographics\/ACM SIGGRAPH symposium on Geometry processing (SGP\u201903). Eurographics Association Goslar DEU 146\u2013155."},{"key":"e_1_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015715"},{"key":"e_1_3_1_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01103.x"},{"key":"e_1_3_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_16"},{"key":"e_1_3_1_46_1","unstructured":"Vincent Sitzmann Julien Martel Alexander Bergman David Lindell and Gordon Wetzstein. 2020. Implicit neural representations with periodic activation functions. In Advances in Neural Information Processing Systems 33 10 (2020) 7462\u20137473."},{"key":"e_1_3_1_47_1","volume-title":"International Conference on Learning Representations","author":"Smirnov Dmitriy","year":"2020","unstructured":"Dmitriy Smirnov, Mikhail Bessmeltsev, and Justin Solomon. 2020. Learning manifold patch-based representations of man-made shapes. In International Conference on Learning Representations."},{"key":"e_1_3_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"e_1_3_1_49_1","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/978-3-030-58517-4_18","volume-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI 16","author":"Tretschk Edgar","year":"2020","unstructured":"Edgar Tretschk, Ayush Tewari, Vladislav Golyanik, Michael Zollh\u00f6fer, Carsten Stoll, and Christian Theobalt. 2020. Patchnets: Patch-based generalizable deep implicit 3d shape representations. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI 16. Springer, 293\u2013309."},{"key":"e_1_3_1_50_1","article-title":"A topology-preserving optimization algorithm for polycube mapping","volume":"35","author":"Wan Shenghua","year":"2011","unstructured":"Shenghua Wan, Zhao Yin, Kang Zhang, Hongchao Zhang, and Xin Li. 2011. A topology-preserving optimization algorithm for polycube mapping. Computers and Graphics 35, 3 (2011), 639\u2013649.","journal-title":"Computers and Graphics"},{"key":"e_1_3_1_51_1","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1145\/1236246.1236281","volume-title":"Proceedings of the 2007 ACM Symposium on Solid and Physical Modeling","author":"Wang Hongyu","year":"2007","unstructured":"Hongyu Wang, Ying He, Xin Li, Xianfeng Gu, and Hong Qin. 2007. Polycube splines. In Proceedings of the 2007 ACM Symposium on Solid and Physical Modeling. 241\u2013251."},{"key":"e_1_3_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275074"},{"key":"e_1_3_1_53_1","unstructured":"Nicholas Watters Loic Matthey Christopher P Burgess and Alexander Lerchner. 2019. Spatial broadcast decoder: A simple architecture for learning disentangled representations in vaes. arXiv:1901.07017. Retrieved from https:\/\/arxiv.org\/abs\/1901.07017"},{"key":"e_1_3_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01037"},{"key":"e_1_3_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"e_1_3_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530100"},{"key":"e_1_3_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555469"},{"key":"e_1_3_1_58_1","unstructured":"Qijian Zhang Junhui Hou Wenping Wang and Ying He. 2024. Flatten anything: Unsupervised neural surface parameterization. arXiv:2405.14633. Retrieved from https:\/\/arxiv.org\/abs\/2405.14633"},{"key":"e_1_3_1_59_1","first-page":"20428","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Zhou Bingyang","year":"2023","unstructured":"Bingyang Zhou, Haoyu Zhou, Tianhai Liang, Qiaojun Yu, Siheng Zhao, Yuwei Zeng, Jun Lv, Siyuan Luo, Qiancai Wang, Xinyuan Yu, et\u00a0al. 2023. Clothesnet: An information-rich 3d garment model repository with simulated clothes environment. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 20428\u201320438."},{"key":"e_1_3_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_30"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3771546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T12:27:41Z","timestamp":1766147261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3771546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3771546"],"URL":"https:\/\/doi.org\/10.1145\/3771546","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"2024-11-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}