{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T10:49:55Z","timestamp":1679482195152},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2017,7,20]],"date-time":"2017-07-20T00:00:00Z","timestamp":1500508800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Israel PBC and ISF","award":["4\/11"]},{"name":"European Research Council","award":["307754)"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2017,8,31]]},"abstract":"The recent success of convolutional neural networks (CNNs) for image processing tasks is inspiring research efforts attempting to achieve similar success for geometric tasks. One of the main challenges in applying CNNs to surfaces is defining a natural convolution operator on surfaces.<\/jats:p>\n In this paper we present a method for applying deep learning to sphere-type shapes using a global seamless parameterization to a planar flat-torus, for which the convolution operator is well defined. As a result, the standard deep learning framework can be readily applied for learning semantic, high-level properties of the shape. An indication of our success in bridging the gap between images and surfaces is the fact that our algorithm succeeds in learning semantic information from an input of raw low-dimensional feature vectors.<\/jats:p>\n We demonstrate the usefulness of our approach by presenting two applications: human body segmentation, and automatic landmark detection on anatomical surfaces. We show that our algorithm compares favorably with competing geometric deep-learning algorithms for segmentation tasks, and is able to produce meaningful correspondences on anatomical surfaces where hand-crafted features are bound to fail.<\/jats:p>","DOI":"10.1145\/3072959.3073616","type":"journal-article","created":{"date-parts":[[2017,7,21]],"date-time":"2017-07-21T12:24:07Z","timestamp":1500639847000},"page":"1-10","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":111,"title":["Convolutional neural networks on surfaces via seamless toric covers"],"prefix":"10.1145","volume":"36","author":[{"given":"Haggai","family":"Maron","sequence":"first","affiliation":[{"name":"Weizmann Institute of Science"}]},{"given":"Meirav","family":"Galun","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science"}]},{"given":"Noam","family":"Aigerman","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science"}]},{"given":"Miri","family":"Trope","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science"}]},{"given":"Nadav","family":"Dym","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science"}]},{"given":"Ersin","family":"Yumer","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Vladimir G.","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Yaron","family":"Lipman","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science"}]}],"member":"320","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"2016. Adobe Fuse 3D Characters. https:\/\/www.mixamo.com. (2016). Accessed: 2016-10-15. 2016. Adobe Fuse 3D Characters. https:\/\/www.mixamo.com. (2016). Accessed: 2016-10-15."},{"key":"e_1_2_2_2_1","unstructured":"2016. Yobi3d - free 3d model search engine. https:\/\/www.yobi3d.com. (2016). Accessed: 2016-10-15. 2016. Yobi3d - free 3d model search engine. https:\/\/www.yobi3d.com. (2016). Accessed: 2016-10-15."},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818099"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982412"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073207"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130444"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.491"},{"key":"e_1_2_2_8_1","volume-title":"Computer Graphics Forum","author":"Boscaini Davide","unstructured":"Davide Boscaini , Jonathan Masci , Simone Melzi , Michael M Bronstein , Umberto Castellani , and Pierre Vandergheynst . 2015. Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks . In Computer Graphics Forum , Vol. 34 . Wiley Online Library , 13--23. Davide Boscaini, Jonathan Masci, Simone Melzi, Michael M Bronstein, Umberto Castellani, and Pierre Vandergheynst. 2015. Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks. In Computer Graphics Forum, Vol. 34. Wiley Online Library, 13--23."},{"key":"e_1_2_2_9_1","volume-title":"Bronstein","author":"Boscaini Davide","year":"2016","unstructured":"Davide Boscaini , Jonathan Masci , Emanuele Rodol\u00e0 , and Michael M . Bronstein . 2016 . Learning shape correspondence with anisotropic convolutional neural networks. In NIPS. Davide Boscaini, Jonathan Masci, Emanuele Rodol\u00e0, and Michael M. Bronstein. 2016. Learning shape correspondence with anisotropic convolutional neural networks. In NIPS."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1112822108"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_2_12_1","volume-title":"Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203","author":"Bruna Joan","year":"2013","unstructured":"Joan Bruna , Wojciech Zaremba , Arthur Szlam , and Yann LeCun . 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 ( 2013 ). Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013)."},{"key":"e_1_2_2_13_1","volume-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062","author":"Chen Liang-Chieh","year":"2014","unstructured":"Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , and Alan L Yuille . 2014. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 ( 2014 ). Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2014. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 (2014)."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618864"},{"key":"e_1_2_2_15_1","unstructured":"Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems. 3837--3845. Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems. 3837--3845."},{"key":"e_1_2_2_16_1","volume-title":"Shape retrieval contest 2007: Watertight models track. SHREC competition 8","author":"Giorgi Daniela","year":"2007","unstructured":"Daniela Giorgi , Silvia Biasotti , and Laura Paraboschi . 2007. Shape retrieval contest 2007: Watertight models track. SHREC competition 8 ( 2007 ). Daniela Giorgi, Silvia Biasotti, and Laura Paraboschi. 2007. Shape retrieval contest 2007: Watertight models track. SHREC competition 8 (2007)."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566589"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835487"},{"key":"e_1_2_2_19_1","volume-title":"Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163","author":"Henaff Mikael","year":"2015","unstructured":"Mikael Henaff , Joan Bruna , and Yann LeCun . 2015. Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 ( 2015 ). Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015)."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015815"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01060.x"},{"key":"e_1_2_2_22_1","volume-title":"3D Shape Segmentation with Projective Convolutional Networks. arXiv preprint arXiv:1612.02808","author":"Kalogerakis Evangelos","year":"2016","unstructured":"Evangelos Kalogerakis , Melinos Averkiou , Subhransu Maji , and Siddhartha Chaudhuri . 2016. 3D Shape Segmentation with Projective Convolutional Networks. arXiv preprint arXiv:1612.02808 ( 2016 ). Evangelos Kalogerakis, Melinos Averkiou, Subhransu Maji, and Siddhartha Chaudhuri. 2016. 3D Shape Segmentation with Projective Convolutional Networks. arXiv preprint arXiv:1612.02808 (2016)."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778839"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964974"},{"key":"e_1_2_2_25_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_2_2_26_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105. Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_2_2_27_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 289--297","author":"Laptev Dmitry","year":"2016","unstructured":"Dmitry Laptev , Nikolay Savinov , Joachim M Buhmann , and Marc Pollefeys . 2016 . TIPOOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 289--297 . Dmitry Laptev, Nikolay Savinov, Joachim M Buhmann, and Marc Pollefeys. 2016. TIPOOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 289--297."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.148"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-5244-1_13"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.112"},{"key":"e_1_2_2_32_1","volume-title":"Topology from a differentiable viewpoint","author":"Milnor J","year":"1965","unstructured":"J Milnor . 1965. Topology from a differentiable viewpoint ( University of Virginia Press , Charlottesville, VA ). ( 1965 ). J Milnor. 1965. Topology from a differentiable viewpoint(University of Virginia Press, Charlottesville, VA). (1965)."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1201775.882274"},{"key":"e_1_2_2_34_1","volume-title":"Guibas","author":"Qi Charles R.","year":"2016","unstructured":"Charles R. Qi , Hao Su , Kaichun Mo , and Leonidas J . Guibas . 2016 a. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation . arXiv preprint arXiv:1612.00593 (2016). Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2016a. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. arXiv preprint arXiv:1612.00593 (2016)."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.532"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_14"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01515.x"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15558-1_26"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1112\/plms\/s3-13.1.743"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1399504.1360696"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.171"},{"key":"e_1_2_2_45_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu , Shuran Song , Aditya Khosla , Fisher Yu , Linguang Zhang , Xiaoou Tang , and Jianxiong Xiao . 2015 . 3d shapenets: A deep representation for volumetric shapes . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920 . Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920."},{"key":"e_1_2_2_46_1","unstructured":"Xinchen Yan Jimei Yang Ersin Yumer Yijie Guo and Honglak Lee. 2016. Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision. In Advances in Neural Information Processing Systems. 1696--1704. Xinchen Yan Jimei Yang Ersin Yumer Yijie Guo and Honglak Lee. 2016. Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision. In Advances in Neural Information Processing Systems. 1696--1704."},{"key":"e_1_2_2_47_1","volume-title":"SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. arXiv preprint arXiv:1612.00606","author":"Yi Li","year":"2016","unstructured":"Li Yi , Hao Su , Xingwen Guo , and Leonidas Guibas . 2016. SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. arXiv preprint arXiv:1612.00606 ( 2016 ). Li Yi, Hao Su, Xingwen Guo, and Leonidas Guibas. 2016. SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. arXiv preprint arXiv:1612.00606 (2016)."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.2000.0875"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,31]],"date-time":"2022-12-31T10:25:41Z","timestamp":1672482341000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073616"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,20]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8,31]]}},"alternative-id":["10.1145\/3072959.3073616"],"URL":"http:\/\/dx.doi.org\/10.1145\/3072959.3073616","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":["Computer Graphics and Computer-Aided Design"],"published":{"date-parts":[[2017,7,20]]},"assertion":[{"value":"2017-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}