{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:14:12Z","timestamp":1756311252727},"reference-count":46,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T00:00:00Z","timestamp":1565568000000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We propose a self\u2010supervised approach to deep surface deformation. Given a pair of shapes, our algorithm directly predicts a parametric transformation from one shape to the other respecting correspondences. Our insight is to use cycle\u2010consistency to define a notion of good correspondences in groups of objects and use it as a supervisory signal to train our network. Our method combines does not rely on a template, assume near isometric deformations or rely on point\u2010correspondence supervision. We demonstrate the efficacy of our approach by using it to transfer segmentation across shapes. We show, on Shapenet, that our approach is competitive with comparable state\u2010of\u2010the\u2010art methods when annotated training data is readily available, but outperforms them by a large margin in the few\u2010shot segmentation scenario.<\/jats:p>","DOI":"10.1111\/cgf.13794","type":"journal-article","created":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T07:13:00Z","timestamp":1565593980000},"page":"123-133","update-policy":"http:\/\/dx.doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Unsupervised cycle\u2010consistent deformation for shape matching"],"prefix":"10.1111","volume":"38","author":[{"given":"Thibault","family":"Groueix","sequence":"first","affiliation":[{"name":"LIGM (UMR 8049), \u00c9cole des Ponts, UPE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Fisher","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir G.","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan C.","family":"Russell","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Aubry","sequence":"additional","affiliation":[{"name":"LIGM (UMR 8049), \u00c9cole des Ponts, UPE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,8,12]]},"reference":[{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073696"},{"key":"e_1_2_8_3_2","doi-asserted-by":"crossref","unstructured":"BronsteinA. M. BronsteinM. M. KimmelR.: Generalized multidimensional scaling: A framework for isometry\u2010invariant partial surface matching.Proceedings of the National Academy of Sciences103 5 (2006) 1168\u20131172. 2","DOI":"10.1073\/pnas.0508601103"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"e_1_2_8_5_2","unstructured":"BoscainiD. MasciJ. Rodol\u00e0E. BronsteinM. M.: Learning shape correspondence with anisotropic convolutional neural networks.CoRR abs\/1605.06437(2016). 2"},{"key":"e_1_2_8_6_2","doi-asserted-by":"crossref","unstructured":"BrownB. RusinkiewiczS.: Global non\u2010rigid alignment of 3\u2010D scans.ACM Transactions on Graphics (Proc. SIGGRAPH)26 3 (Aug.2007). 1 2","DOI":"10.1145\/1276377.1276404"},{"key":"e_1_2_8_7_2","unstructured":"ChangA. X. FunkhouserT. A. GuibasL. J. HanrahanP. HuangQ. LiZ. SavareseS. SavvaM. SongS. SuH. XiaoJ. YiL. YuF.: Shapenet: An information\u2010rich 3d model repository.CoRR abs\/1512.03012(2015). 3"},{"key":"e_1_2_8_8_2","doi-asserted-by":"crossref","unstructured":"ChenQ. KoltunV.: Robust nonrigid registration by convex optimization.ICCV(2015). 1 2","DOI":"10.1109\/ICCV.2015.236"},{"key":"e_1_2_8_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13254"},{"key":"e_1_2_8_10_2","doi-asserted-by":"crossref","unstructured":"GroueixT. FisherM. KimV. G. RussellB. AubryM.: 3d\u2010coded: 3d correspondences by deep deformation. InECCV(2018). 2 3 5","DOI":"10.1007\/978-3-030-01216-8_15"},{"key":"e_1_2_8_11_2","doi-asserted-by":"crossref","unstructured":"GroueixT. FisherM. KimV. G. RussellB. AubryM.: AtlasNet: A Papier\u2010M\u00e2ch\u00e9 Approach to Learning 3D Surface Generation. InProceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)(2018). 2 5 7","DOI":"10.1109\/CVPR.2018.00030"},{"key":"e_1_2_8_12_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01285.x"},{"key":"e_1_2_8_13_2","doi-asserted-by":"crossref","unstructured":"HuangQ.\u2010X. GuibasL.: Consistent shape maps via semidefinite programming. InProceedings of the Eleventh Eurographics\/ACMSIGGRAPH Symposium on Geometry Processing(Aire\u2010la\u2010Ville Switzerland Switzerland 2013) SGP '13 Eurographics Association pp.177\u2013186. 1 2","DOI":"10.1111\/cgf.12184"},{"key":"e_1_2_8_14_2","unstructured":"HuangH. KalogerakisE. ChaudhuriS. CeylanD. KimV. G. YumerE.: Learning local shape descriptors from part correspondences with multi\u2010view convolutional networks.Transactions on Graphics(2018). 2"},{"key":"e_1_2_8_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366186"},{"key":"e_1_2_8_16_2","unstructured":"JaderbergM. SimonyanK. ZissermanA. et al.: Spatial transformer networks. InAdvances in neural information processing systems(2015) pp.2017\u20132025. 3"},{"key":"e_1_2_8_17_2","doi-asserted-by":"crossref","unstructured":"KalogerakisE. AverkiouM. MajiS. ChaudhuriS.: 3D shape segmentation with projective convolutional networks. InProc. IEEE Computer Vision and Pattern Recognition (CVPR)(2017). 3","DOI":"10.1109\/CVPR.2017.702"},{"key":"e_1_2_8_18_2","unstructured":"KingmaD. P. BaJ.: Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980(2014). 3"},{"issue":"3","key":"e_1_2_8_19_2","article-title":"Learning 3D Mesh Segmentation and Labeling","volume":"29","author":"Kalogerakis E.","year":"2010","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_2_8_20_2","unstructured":"KimV. G. LipmanY. FunkhouserT.: Blended intrinsic maps.Transactions on Graphics (Proc. of SIGGRAPH) 4 (2011). 1 2 3"},{"key":"e_1_2_8_21_2","doi-asserted-by":"crossref","unstructured":"KimV. G. LiW. MitraN. J. DiVerdiS. FunkhouserT.: Exploring Collections of 3D Models using Fuzzy Correspondences.Transactions on Graphics (Proc. of SIGGRAPH) 4 (2012). 1 2","DOI":"10.1145\/2185520.2185550"},{"key":"e_1_2_8_22_2","unstructured":"KanazawaA. TulsianiS. EfrosA. A. MalikJ.:Learning category\u2010specific mesh reconstruction from image collections. 5"},{"key":"e_1_2_8_23_2","doi-asserted-by":"crossref","unstructured":"LitanyO. RemezT. Rodol\u00e0E. BronsteinA. M. BronsteinM. M.: Deep functional maps: Structured prediction for dense shape correspondence.CoRR abs\/1704.08686(2017). 2","DOI":"10.1109\/ICCV.2017.603"},{"key":"e_1_2_8_24_2","doi-asserted-by":"crossref","unstructured":"LiL. SungM. DubrovinaA. YiL. GuibasL. J.: Supervised fitting of geometric primitives to 3d point clouds.CVPR(2018). 1 3","DOI":"10.1109\/CVPR.2019.00276"},{"key":"e_1_2_8_25_2","doi-asserted-by":"crossref","unstructured":"LiH. SumnerR. W. PaulyM.: Global correspondence optimization for non\u2010rigid registration of depth scans.Computer Graphics Forum (Proc. SGP'08)27 5 (July2008). 2","DOI":"10.1111\/j.1467-8659.2008.01282.x"},{"key":"e_1_2_8_26_2","doi-asserted-by":"crossref","unstructured":"MitraN. J. WandM. ZhangH. Cohen\u2010OrD. KimV. G. HuangQ.\u2010X.: Structure\u2010Aware Shape Processing.SIGGRAPH Course notes(2014). 1","DOI":"10.1145\/2614028.2615401"},{"key":"e_1_2_8_27_2","unstructured":"MoK. ZhuS. ChangA. YiL. TripathiS. GuibasL. SuH.:PartNet: A large\u2010scale benchmark for fine\u2010grained and hierarchical part\u2010level 3D object understanding. 1"},{"key":"e_1_2_8_28_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02022.x"},{"key":"e_1_2_8_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185526"},{"key":"e_1_2_8_30_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2010.01764.x"},{"key":"e_1_2_8_31_2","unstructured":"QiC. R. SuH. MoK. GuibasL. J.: Pointnet: Deep learning on point sets for 3d classification and segmentation.arXiv preprint arXiv:1612.00593(2016). 1 2 3 5 7 8 9"},{"key":"e_1_2_8_32_2","unstructured":"QiC. R. YiL. SuH. GuibasL. J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space.arXiv preprint arXiv:1706.02413(2017). 1 3"},{"key":"e_1_2_8_33_2","unstructured":"RusinkiewiczS. LevoyM.: Efficient variants of the icp algorithm. InProceedings Third International Conference on 3\u2010D Digital Imaging and Modeling(2001). 1 2"},{"key":"e_1_2_8_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461959"},{"key":"e_1_2_8_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275040"},{"key":"e_1_2_8_36_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01884.x"},{"key":"e_1_2_8_37_2","doi-asserted-by":"crossref","unstructured":"WeiL. HuangQ. CeylanD. VougaE. LiH.: Dense human body correspondences using convolutional networks. InComputer Vision and Pattern Recognition (CVPR)(2016). 2","DOI":"10.1109\/CVPR.2016.171"},{"key":"e_1_2_8_38_2","unstructured":"WangY. SunY. LiuZ. SarmaS. E. BronsteinM. M. SolomonJ. M.: Dynamic graph CNN for learning on point clouds.CoRR abs\/1801.07829(2018). 1 3"},{"key":"e_1_2_8_39_2","doi-asserted-by":"crossref","unstructured":"WangN. ZhangY. LiZ. FuY. LiuW. JiangY.\u2010G.: Pixel2mesh: Generating 3d mesh models from single rgb images. InECCV(2018). 5","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"e_1_2_8_40_2","doi-asserted-by":"crossref","unstructured":"WangX. ZhouB. ShiY. ChenX. ZhaoQ. XuK.: Shape2motion: Joint analysis of motion parts and attributes from 3d shapes. InCVPR(2019) p. to appear. 1","DOI":"10.1109\/CVPR.2019.00908"},{"key":"e_1_2_8_41_2","doi-asserted-by":"crossref","unstructured":"YiL. KimV. G. CeylanD. ShenI.\u2010C. YanM. SuH. LuC. HuangQ. ShefferA. GuibasL.: A scalable active framework for region annotation in 3d shape collections.SIGGRAPH Asia(2016). 1 2 3 5","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_2_8_42_2","doi-asserted-by":"crossref","unstructured":"YuF. LiuK. ZhangY. ZhuC. XuK.: Partnet: A recursive part decomposition network for fine\u2010grained and hierarchical shape segmentation. InCVPR(2019) p. to appear. 1","DOI":"10.1109\/CVPR.2019.00972"},{"key":"e_1_2_8_43_2","doi-asserted-by":"crossref","unstructured":"ZhangZ.:Iterative point matching for registration of free\u2010form curves and surfaces 1994. 5","DOI":"10.1007\/BF01427149"},{"key":"e_1_2_8_44_2","doi-asserted-by":"crossref","unstructured":"ZhouT. Kr\u00e4henb\u00fchlP. AubryM. HuangQ. EfrosA. A.: Learning dense correspondence via 3d\u2010guided cycle consistency. InComputer Vision and Pattern Recognition (CVPR)(2016). 2","DOI":"10.1109\/CVPR.2016.20"},{"key":"e_1_2_8_45_2","doi-asserted-by":"crossref","unstructured":"ZhuJ.\u2010Y. ParkT. IsolaP. EfrosA. A.: Unpaired image\u2010to\u2010image translation using cycle\u2010consistent adversarial networks. InComputer Vision (ICCV) 2017 IEEE International Conference on(2017). 3","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_8_46_2","unstructured":"ZhouQ.\u2010Y. ParkJ. KoltunV.: Open3D: A modern library for 3D data processing.arXiv:1801.09847(2018). 8"},{"key":"e_1_2_8_47_2","doi-asserted-by":"crossref","unstructured":"ZhangH. ShefferA. Cohen\u2010OrD. ZhouQ. vanKaickO. TagliasacchiA.: Deformation\u2010drive shape correspondence.Computer Graphics Forum (Special Issue of Symposium on Geometry Processing)27 5 (2008) 1431\u20131439. 2","DOI":"10.1111\/j.1467-8659.2008.01283.x"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fcgf.13794","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.13794","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.13794","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.13794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T04:15:23Z","timestamp":1694319323000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.13794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["10.1111\/cgf.13794"],"URL":"https:\/\/doi.org\/10.1111\/cgf.13794","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]},"assertion":[{"value":"2019-08-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}