{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T17:13:10Z","timestamp":1780679590304,"version":"3.54.1"},"reference-count":80,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1945954,1925596"],"award-info":[{"award-number":["1945954,1925596"]}],"id":[{"id":"10.13039\/100000001","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":[[2022,12]]},"abstract":"<jats:p>We introduce DeepJoin, an automated approach to generate high-resolution repairs for fractured shapes using deep neural networks. Existing approaches to perform automated shape repair operate exclusively on symmetric objects, require a complete proxy shape, or predict restoration shapes using low-resolution voxels which are too coarse for physical repair. We generate a high-resolution restoration shape by inferring a corresponding complete shape and a break surface from an input fractured shape. We present a novel implicit shape representation for fractured shape repair that combines the occupancy function, signed distance function, and normal field. We demonstrate repairs using our approach for synthetically fractured objects from ShapeNet, 3D scans from the Google Scanned Objects dataset, objects in the style of ancient Greek pottery from the QP Cultural Heritage dataset, and real fractured objects. We outperform six baseline approaches in terms of chamfer distance and normal consistency. Unlike existing approaches and restorations generated using subtraction, DeepJoin restorations do not exhibit surface artifacts and join closely to the fractured region of the fractured shape. Our code is available at: https:\/\/github.com\/Terascale-All-sensing-Research-Studio\/DeepJoin.<\/jats:p>","DOI":"10.1145\/3550454.3555470","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T21:19:07Z","timestamp":1669843147000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["DeepJoin"],"prefix":"10.1145","volume":"41","author":[{"given":"Nikolas","family":"Lamb","sequence":"first","affiliation":[{"name":"Clarkson University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Clarkson University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natasha Kholgade","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Clarkson University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"International conference on machine learning. International conference on machine learning 80","author":"Achlioptas Panos","year":"2018","unstructured":"Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, and Leonidas Guibas. 2018. Learning representations and generative models for 3d point clouds, In International conference on machine learning. International conference on machine learning 80, 35, 40--49."},{"key":"e_1_2_2_2_1","volume-title":"VAST (Short and Project Papers)","author":"Antlej Kaja","unstructured":"Kaja Antlej, Miran Eric, Mojca Savnik, Bernarda Zupanek, Janja Slabe, and B Borut Battestin. 2011. Combining 3D Technologies in the Field of Cultural Heritage: Three Case Studies.. In VAST (Short and Project Papers). The Eurographics Association, Geneve, Switzerland, 1--4."},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.642"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-0737-8_8"},{"key":"e_1_2_2_5_1","volume-title":"Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint arXiv:1608.04236 1, 1","author":"Brock Andrew","year":"2016","unstructured":"Andrew Brock, Theodore Lim, James M Ritchie, and Nick Weston. 2016. Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint arXiv:1608.04236 1, 1 (2016), 1--9."},{"key":"e_1_2_2_6_1","volume-title":"Deep local shapes: Learning local sdf priors for detailed 3d reconstruction","author":"Chabra Rohan","unstructured":"Rohan Chabra, Jan E Lenssen, Eddy Ilg, Tanner Schmidt, Julian Straub, Steven Lovegrove, and Richard Newcombe. 2020. Deep local shapes: Learning local sdf priors for detailed 3d reconstruction. In ECCV. Springer, Berlin, Germany, 608--625."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01284"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00700"},{"key":"e_1_2_2_11_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. Advances in Neural Information Processing Systems 33 (2020), 21638--21652.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00093"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00481"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.693"},{"key":"e_1_2_2_15_1","volume-title":"Surface normal estimation of tilted images via spatial rectifier","author":"Do Tien","unstructured":"Tien Do, Khiem Vuong, Stergios I Roumeliotis, and Hyun Soo Park. 2020. Surface normal estimation of tilted images via spatial rectifier. In ECCV. Springer, Springer, Berlin, Germany, 265--280."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275006"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_4"},{"key":"e_1_2_2_18_1","volume-title":"Constructive theory of functions of several variables","author":"Duchon Jean","unstructured":"Jean Duchon. 1977. Splines minimizing rotation-invariant semi-norms in Sobolev spaces. In Constructive theory of functions of several variables. Springer, Berlin, Germany, 85--100."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00035"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-006-0923-6"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00491"},{"key":"e_1_2_2_23_1","unstructured":"GoogleResearch. 2022. Google Scanned Objects. Open Robotics. https:\/\/fuel.gazebosim.org\/1.0\/GoogleResearch\/fuel\/collections\/Google%20Scanned%20Objects"},{"key":"e_1_2_2_24_1","volume-title":"GCH","author":"Gregor Robert","unstructured":"Robert Gregor, Ivan Sipiran, Georgios Papaioannou, Tobias Schreck, Anthousis Andreadis, and Pavlos Mavridis. 2014. Towards Automated 3D Reconstruction of Defective Cultural Heritage Objects.. In GCH. EUROGRAPHICS, Geneva, Switzerland, 135--144."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00030"},{"key":"e_1_2_2_26_1","volume-title":"Theory of T-norms and fuzzy inference methods. Fuzzy sets and systems 40, 3","author":"Gupta Madan M","year":"1991","unstructured":"Madan M Gupta and J11043360726 Qi. 1991. Theory of T-norms and fuzzy inference methods. Fuzzy sets and systems 40, 3 (1991), 431--450."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.19"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00765"},{"key":"e_1_2_2_29_1","volume-title":"Custom-designed orthopedic implants evaluated using finite element analysis of patient-specific computed tomography data: femoral-component case study. BMC musculoskeletal disorders 8, 1","author":"Harrysson Ola LA","year":"2007","unstructured":"Ola LA Harrysson, Yasser A Hosni, and Jamal F Nayfeh. 2007. Custom-designed orthopedic implants evaluated using finite element analysis of patient-specific computed tomography data: femoral-component case study. BMC musculoskeletal disorders 8, 1 (2007), 1--10."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208159.3208173"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00501"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00873"},{"key":"e_1_2_2_33_1","volume-title":"Learning Occupancy Function from Point Clouds for Surface Reconstruction. arXiv preprint arXiv:2010.11378 1","author":"Jia Meng","year":"2020","unstructured":"Meng Jia and Matthew Kyan. 2020. Learning Occupancy Function from Point Clouds for Surface Reconstruction. arXiv preprint arXiv:2010.11378 1 (2020), 1--11."},{"key":"e_1_2_2_34_1","first-page":"8776","article-title":"UCSG-NET-unsupervised discovering of constructive solid geometry tree","volume":"33","author":"Kania Kacper","year":"2020","unstructured":"Kacper Kania, Maciej Zieba, and Tomasz Kajdanowicz. 2020. UCSG-NET-unsupervised discovering of constructive solid geometry tree. Advances in Neural Information Processing Systems 33 (2020), 8776--8786.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_35_1","volume-title":"Proc. ICLR. International Conference on Representation Learning","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In Proc. ICLR. International Conference on Representation Learning, La Jolla, CA, 1--15."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.culher.2008.07.012"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3328939.3329005"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485114.3485118"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01126"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00308"},{"key":"e_1_2_2_41_1","volume-title":"SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images. arXiv preprint arXiv:2010.10505 1, 1","author":"Lin Chen-Hsuan","year":"2020","unstructured":"Chen-Hsuan Lin, Chaoyang Wang, and Simon Lucey. 2020. SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images. arXiv preprint arXiv:2010.10505 1, 1 (2020), 1--17."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00187"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6827"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"e_1_2_2_45_1","volume-title":"Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces. arXiv preprint arXiv:2011.13495 1, 1","author":"Ma Baorui","year":"2020","unstructured":"Baorui Ma, Zhizhong Han, Yu-Shen Liu, and Matthias Zwicker. 2020. Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces. arXiv preprint arXiv:2011.13495 1, 1 (2020), 1--12."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00842"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3009905"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_2_2_50_1","volume-title":"Proceedings, Part III 16","author":"Peng Songyou","year":"2020","unstructured":"Songyou Peng, Michael Niemeyer, Lars Mescheder, Marc Pollefeys, and Andreas Geiger. 2020. Convolutional occupancy networks. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part III 16. Springer, Berlin, Germany, 523--540."},{"key":"e_1_2_2_51_1","volume-title":"The NURBS book","author":"Piegl Les","unstructured":"Les Piegl and Wayne Tiller. 1996. The NURBS book. Springer Science & Business Media, Berlin, Germany."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_39"},{"key":"e_1_2_2_53_1","volume-title":"Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30","author":"Qi Charles Ruizhongtai","year":"2017","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 (2017), 1--10."},{"key":"e_1_2_2_54_1","volume-title":"Christian M Zechmann, Roland Unterhinninghofen, H-U Kauczor, and Frederik L Giesel.","author":"Rengier Fabian","year":"2010","unstructured":"Fabian Rengier, Amit Mehndiratta, Hendrik Von Tengg-Kobligk, Christian M Zechmann, Roland Unterhinninghofen, H-U Kauczor, and Frederik L Giesel. 2010. 3D printing based on imaging data: review of medical applications. International journal of computer assisted radiology and surgery 5, 4 (2010), 335--341."},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00605"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.13130666"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2011.196"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1108\/RPJ-09-2016-0148"},{"key":"e_1_2_2_59_1","volume-title":"Vconv-dae: Deep volumetric shape learning without object labels","author":"Sharma Abhishek","year":"2016","unstructured":"Abhishek Sharma, Oliver Grau, and Mario Fritz. 2016. Vconv-dae: Deep volumetric shape learning without object labels. In ECCV. Springer, Berlin, Germany, 236--250."},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00578"},{"key":"e_1_2_2_61_1","volume-title":"Metasdf: Meta-learning signed distance functions. arXiv preprint arXiv:2006.09662 1, 1","author":"Sitzmann Vincent","year":"2020","unstructured":"Vincent Sitzmann, Eric R Chan, Richard Tucker, Noah Snavely, and Gordon Wetzstein. 2020. Metasdf: Meta-learning signed distance functions. arXiv preprint arXiv:2006.09662 1, 1 (2020), 1--17."},{"key":"e_1_2_2_62_1","volume-title":"Conference on Robot Learning. PMLR","author":"Smith Edward J","year":"2017","unstructured":"Edward J Smith and David Meger. 2017. Improved adversarial systems for 3d object generation and reconstruction. In Conference on Robot Learning. PMLR, Cambridge, UK, 87--96."},{"key":"e_1_2_2_63_1","volume-title":"SAUM: Symmetry-Aware Upsampling Module for Consistent Point Cloud Completion. In Proc","author":"Son Hyeontae","year":"2020","unstructured":"Hyeontae Son and Young Min Kim. 2020. SAUM: Symmetry-Aware Upsampling Module for Consistent Point Cloud Completion. In Proc. ACCV. Springer, Berlin, Germany, 1--17."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1126-y"},{"key":"e_1_2_2_66_1","volume-title":"Deep Surface Reconstruction from Point Clouds with Visibility Information. arXiv preprint arXiv:2202.01810 1, 1","author":"Sulzer Raphael","year":"2022","unstructured":"Raphael Sulzer, Loic Landrieu, Alexandre Boulch, Renaud Marlet, and Bruno Vallet. 2022. Deep Surface Reconstruction from Point Clouds with Visibility Information. arXiv preprint arXiv:2202.01810 1, 1 (2022), 1--13."},{"key":"e_1_2_2_67_1","volume-title":"Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks. arXiv preprint arXiv:2105.03582 1, 1","author":"Tang Jiapeng","year":"2021","unstructured":"Jiapeng Tang, Jiabao Lei, Dan Xu, Feiying Ma, Kui Jia, and Lei Zhang. 2021. Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks. arXiv preprint arXiv:2105.03582 1, 1 (2021), 1--16."},{"key":"e_1_2_2_68_1","volume-title":"Proc","author":"Tretschk Edgar","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 Proc. ECCV. Springer, Berlin, Germany, 293--309."},{"key":"e_1_2_2_69_1","volume-title":"DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces. arXiv preprint arXiv:2011.02570 1, 1","author":"Venkatesh Rahul","year":"2020","unstructured":"Rahul Venkatesh, Sarthak Sharma, Aurobrata Ghosh, Laszlo Jeni, and Maneesh Singh. 2020. DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces. arXiv preprint arXiv:2011.02570 1, 1 (2020), 1--9."},{"key":"e_1_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1097\/GOX.0000000000001093"},{"key":"e_1_2_2_71_1","volume-title":"Proc. NeurIPS. Neural Information Processing Systems","author":"Wu Jiajun","year":"2016","unstructured":"Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T Freeman, and Joshua B Tenenbaum. 2016. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In Proc. NeurIPS. Neural Information Processing Systems, San Diego, CA, 82--90."},{"key":"e_1_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_15"},{"key":"e_1_2_2_73_1","volume-title":"Implicit Autoencoder for Point Cloud Self-supervised Representation Learning. arXiv preprint arXiv:2201.00785 1, 1","author":"Yan Siming","year":"2022","unstructured":"Siming Yan, Zhenpei Yang, Haoxiang Li, Li Guan, Hao Kang, Gang Hua, and Qixing Huang. 2022b. Implicit Autoencoder for Point Cloud Self-supervised Representation Learning. arXiv preprint arXiv:2201.00785 1, 1 (2022), 1--24."},{"key":"e_1_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00614"},{"key":"e_1_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00328"},{"key":"e_1_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01511"},{"key":"e_1_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108395"},{"key":"e_1_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00088"},{"key":"e_1_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_45"},{"key":"e_1_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-003-1990-6"},{"key":"e_1_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00148"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555470","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555470","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:43Z","timestamp":1750182703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555470"}},"subtitle":["Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair"],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":80,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1145\/3550454.3555470"],"URL":"https:\/\/doi.org\/10.1145\/3550454.3555470","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"}}]}}