{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T10:45:24Z","timestamp":1693737924126},"reference-count":51,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003382","name":"Core Research for Evolutional Science and Technology","doi-asserted-by":"publisher","award":["JPMJCR17A1"],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["SFB\/TRR 109"],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2021,2]]},"abstract":"Abstract<\/jats:title>This paper introduces a generative model for 3D surfaces based on a representation of shapes with mean curvature and metric, which are invariant under rigid transformation. Hence, compared with existing 3D machine learning frameworks, our model substantially reduces the influence of translation and rotation. In addition, the local structure of shapes will be more precisely captured, since the curvature is explicitly encoded in our model. Specifically, every surface is first conformally mapped to a canonical domain, such as a unit disk or a unit sphere. Then, it is represented by two functions: the mean curvature half\u2010density and the vertex density, over this canonical domain. Assuming that input shapes follow a certain distribution in a latent space, we use the variational autoencoder to learn the latent space representation. After the learning, we can generate variations of shapes by randomly sampling the distribution in the latent space. Surfaces with triangular meshes can be reconstructed from the generated data by applying isotropic remeshing and spin transformation, which is given by Dirac equation. We demonstrate the effectiveness of our model on datasets of man\u2010made and biological shapes and compare the results with other methods.<\/jats:p>","DOI":"10.1111\/cgf.14094","type":"journal-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T20:58:59Z","timestamp":1602536339000},"page":"38-53","update-policy":"http:\/\/dx.doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Curvature and Density\u2010based Generative Representation of Shapes"],"prefix":"10.1111","volume":"40","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-1582-6991","authenticated-orcid":false,"given":"Z.","family":"Ye","sequence":"first","affiliation":[{"name":"TU Munich Germany"}]},{"given":"N.","family":"Umetani","sequence":"additional","affiliation":[{"name":"The University of Tokyo Japan"}]},{"given":"T.","family":"Igarashi","sequence":"additional","affiliation":[{"name":"The University of Tokyo Japan"}]},{"given":"T.","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"TU Munich Germany"}]}],"member":"311","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_2_10_2_1","unstructured":"[AAB*15]\u00a0AbadiM. AgarwalA. BarhamP. BrevdoE. ChenZ. CitroC. CorradoG. S. DavisA. DeanJ. DevinM. GhemawatS. GoodfellowI. HarpA. IrvingG. IsardM. JiaY. JozefowiczR. KaiserL. KudlurM. LevenbergJ. Man\u00e9D. MongaR. MooreS. MurrayD. OlahC. SchusterM. ShlensJ. SteinerB. SutskeverI. TalwarK. TuckerP. VanhouckeV. VasudevanV. Vi\u00e9gasF. VinyalsO. WardenP. WattenbergM. WickeM. YuY. ZhengX.:TensorFlow: Large\u2010scale machine learning on heterogeneous systems 2015. Software available from tensorflow.org. URL:https:\/\/www.tensorflow.org\/. Accessed: 2019\u201001\u201001"},{"key":"e_1_2_10_3_1","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume":"80","author":"Achlioptas P.","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2003.1199601"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130444"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13503"},{"key":"e_1_2_10_8_1","volume-title":"SIGGRAPH Asia 2018 Technical Papers on \u2010 SIGGRAPH Asia '18","author":"Ben\u2010Hamu H.","year":"2018"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1112822108"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12693"},{"key":"e_1_2_10_11_1","first-page":"27","article-title":"Memoire sur la theorie des surfaces applicables","author":"Bonnet O.","year":"1967","journal-title":"JEC Polyt 42"},{"key":"e_1_2_10_12_1","volume-title":"Proceedings of ICLR, 2014","author":"Bruna J.","year":"2014"},{"key":"e_1_2_10_13_1","article-title":"ShapeNet: An Information\u2010Rich 3D Model Repository","author":"Chang A. X.","year":"2015","journal-title":"arXiv preprint arXiv:1512.03012."},{"key":"e_1_2_10_14_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Cohen T. S.","year":"2018"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201276"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-015-9998-2"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/130950008"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964999"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461986"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766916"},{"key":"e_1_2_10_21_1","first-page":"3844","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Defferrard M.","year":"2016"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144599352836"},{"key":"e_1_2_10_23_1","first-page":"9","volume-title":"VMV","author":"Fuhrmann S.","year":"2010"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"e_1_2_10_25_1","volume-title":"Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Groueix T.","year":"2018"},{"key":"e_1_2_10_26_1","article-title":"CHARMS: a simple framework for adaptive simulation","volume":"3","author":"Grinspun E.","year":"2002","journal-title":"ACM Transactions on Graphics 21"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.831226"},{"key":"e_1_2_10_28_1","unstructured":"[J*18]\u00a0JacobsonA. et\u00a0al.:gptoolbox: Geometry processing toolbox 2018.http:\/\/github.com\/alecjacobson\/gptoolbox. Accessed: 2019\u201001\u201001"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1090\/S1079-6762-98-00040-7"},{"key":"e_1_2_10_30_1","article-title":"Surface networks","author":"Kostrikov I.","year":"2018","journal-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1215\/S0012-7094-98-09219-5"},{"key":"e_1_2_10_32_1","volume-title":"Proceedings of ICLR, 2017","author":"Kipf T. N.","year":"2017"},{"key":"e_1_2_10_33_1","article-title":"A dirac operator for extrinsic shape analysis","volume":"5","author":"Liu D.","year":"2017","journal-title":"Computer Graphics Forum (SGP) 36"},{"key":"e_1_2_10_34_1","first-page":"37","article-title":"Geodesic convolutional neural networks on riemannian manifolds","author":"Masci J.","year":"2015","journal-title":"Proc. of the IEEE International Conference on Computer Vision (ICCV) Workshops"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21407"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073616"},{"key":"e_1_2_10_38_1","first-page":"1","article-title":"The shape variational autoencoder: A deep generative model of part\u2010segmented 3D objects","volume":"5","author":"Nash C.","year":"2017","journal-title":"Computer Graphics Forum 36"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/0040-9383(85)90013-8"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.07.020"},{"key":"e_1_2_10_41_1","first-page":"109","volume-title":"Symposium on Geometry Processing","author":"Sorkine O.","year":"2007"},{"key":"e_1_2_10_42_1","first-page":"5:1","article-title":"Boundary first flattening","volume":"1","author":"Sawhney R.","year":"2017","journal-title":"ACM Transactions on Graphics 37"},{"key":"e_1_2_10_43_1","first-page":"87","article-title":"Improved Adversarial Systems for 3D Object Generation and Reconstruction","volume":"78","author":"Smith E. J.","year":"2017","journal-title":"Proceedings of the 1st Annual Conference on Robot Learning"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01515.x"},{"key":"e_1_2_10_45_1","first-page":"77","volume-title":"ACM Transactions on Graphics (TOG)","author":"Springborn B.","year":"2008"},{"key":"e_1_2_10_46_1","first-page":"2088","article-title":"Octree Generating Networks: Efficient Convolutional Architectures for High\u2010Resolution 3D Outputs","author":"Tatarchenko M.","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00409"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3145749.3145758"},{"key":"e_1_2_10_49_1","first-page":"72:1","article-title":"O\u2010cnn: octree\u2010based convolutional neural networks for 3D shape analysis","author":"Wang P.\u2010S.","year":"2017","journal-title":"ACM Transactions on Graphics 36"},{"key":"e_1_2_10_50_1","volume-title":"SIGGRAPH Asia 2018 Technical Papers on \u2010 SIGGRAPH Asia '18","author":"Wang P.\u2010S.","year":"2018"},{"key":"e_1_2_10_51_1","first-page":"82","article-title":"Learning a probabilistic latent space of object shapes via 3D generative\u2010adversarial modeling","author":"Wu J.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13494"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14094","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.14094","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14094","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T22:19:15Z","timestamp":1693693155000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.14094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["10.1111\/cgf.14094"],"URL":"http:\/\/dx.doi.org\/10.1111\/cgf.14094","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
