{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T00:13:07Z","timestamp":1725581587983},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"Beijing Natural Science Foundation","award":["L182059"]},{"name":"Shenzhen Basic Research Program","award":["JCYJ20180507182222355"]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61620106003, 61772523, 61802406 and 61972459"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Alibaba Group through Alibaba Innovative Research Program"},{"name":"the CCF-Tencent Open Research Fund"},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFB2100602 and 2019YFB2204104"],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"KAUST OSR Award","award":["CRG-2017-3426"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2020,8,31]]},"abstract":"\n We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets to decompose the Dirichlet energy on a surface. We call this new feature\n Wavelet Energy Decomposition Signature<\/jats:italic>\n (WEDS). Second, we propose a new\n Multiscale Graph Convolutional Network<\/jats:italic>\n (MGCN) to transform a non-learned feature to a more discriminative descriptor. Our results show that the new descriptor WEDS is more discriminative than the current state-of-the-art non-learned descriptors and that the combination of WEDS and MGCN is better than the state-of-the-art learned descriptors. An important design criterion for our descriptor is the robustness to different surface discretizations including triangulations with varying numbers of vertices. Our results demonstrate that previous graph convolutional networks significantly overfit to a particular resolution or even a particular triangulation, but MGCN generalizes well to different surface discretizations. In addition, MGCN is compatible with previous descriptors and it can also be used to improve the performance of other descriptors, such as the heat kernel signature, the wave kernel signature, or the local point signature.\n <\/jats:p>","DOI":"10.1145\/3386569.3392443","type":"journal-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T11:44:27Z","timestamp":1597232667000},"update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["MGCN"],"prefix":"10.1145","volume":"39","author":[{"given":"Yiqun","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences; KAUST"}]},{"given":"Jing","family":"Ren","sequence":"additional","affiliation":[{"name":"Kaust"}]},{"given":"Dong-Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}]},{"given":"Jianwei","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}]},{"given":"Peter","family":"Wonka","sequence":"additional","affiliation":[{"name":"KAUST"}]}],"member":"320","published-online":{"date-parts":[[2020,8,12]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073207"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130444"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12734"},{"volume-title":"FAUST: Dataset and evaluation for 3D mesh registration","year":"2014","author":"Bogo Federica","key":"e_1_2_2_4_1","unstructured":"Federica Bogo, Javier Romero, Matthew Loper, and Michael J Black. 2014. FAUST: Dataset and evaluation for 3D mesh registration. In IEEE Computer Vision and Pattern Recognition (CVPR). 3794--3801."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12693"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12844"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"volume-title":"Scale-invariant heat kernel signatures for non-rigid shape recognition","author":"Bronstein Michael M","key":"e_1_2_2_8_1","unstructured":"Michael M Bronstein and Iasonas Kokkinos. 2010. Scale-invariant heat kernel signatures for non-rigid shape recognition. In IEEE Computer Vision and Pattern Recognition (CVPR). 1704--1711."},{"volume-title":"International Conference on Learning Representations.","year":"2014","author":"Bruna Joan","key":"e_1_2_2_9_1","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann Lecun. 2014. Spectral networks and locally connected networks on graphs. In International Conference on Learning Representations."},{"key":"e_1_2_2_10_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. 3844--3852."},{"volume-title":"Ppfnet: Global context aware local features for robust 3D point matching","year":"2018","author":"Deng Haowen","key":"e_1_2_2_11_1","unstructured":"Haowen Deng, Tolga Birdal, and Slobodan Ilic. 2018. Ppfnet: Global context aware local features for robust 3D point matching. In IEEE Computer Vision and Pattern Recognition (CVPR). 195--205."},{"volume-title":"Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence. arXiv preprint arXiv:2003.14286","year":"2020","author":"Donati Nicolas","key":"e_1_2_2_12_1","unstructured":"Nicolas Donati, Abhishek Sharma, and Maks Ovsjanikov. 2020. Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence. arXiv preprint arXiv:2003.14286 (2020)."},{"volume-title":"Frank Weichert, and Heinrich M\u00fcller.","year":"2018","author":"Fey Matthias","key":"e_1_2_2_13_1","unstructured":"Matthias Fey, Jan Eric Lenssen, Frank Weichert, and Heinrich M\u00fcller. 2018. SplineCNN: Fast geometric deep learning with continuous B-spline kernels. In IEEE Computer Vision and Pattern Recognition (CVPR). 869--877."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24672-5_18"},{"volume-title":"IEEE International Conference on Computer Vision Workshops. 4141--4148","year":"2019","author":"Gong Shunwang","key":"e_1_2_2_15_1","unstructured":"Shunwang Gong, Lei Chen, Michael Bronstein, and Stefanos Zafeiriou. 2019. Spiral-Net++: A Fast and Highly Efficient Mesh Convolution Operator. In IEEE International Conference on Computer Vision Workshops. 4141--4148."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0163-y"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0627-y"},{"volume-title":"Unsupervised learning of dense shape correspondence","author":"Halimi Oshri","key":"e_1_2_2_18_1","unstructured":"Oshri Halimi, Or Litany, Emanuele Rodola, Alex M Bronstein, and Ron Kimmel. 2019. Unsupervised learning of dense shape correspondence. In IEEE Computer Vision and Pattern Recognition (CVPR). 4370--4379."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.04.005"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322959"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3137609"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.765655"},{"volume-title":"Learning compact geometric features","author":"Khoury Marc","key":"e_1_2_2_23_1","unstructured":"Marc Khoury, Qian-Yi Zhou, and Vladlen Koltun. 2017. Learning compact geometric features. In IEEE Computer Vision and Pattern Recognition (CVPR). 153--161."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964974"},{"volume-title":"Kipf and Max Welling","year":"2017","author":"Thomas","key":"e_1_2_2_25_1","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR Posters."},{"volume-title":"European Conference on Computer Vision Workshops . 349--362","year":"2018","author":"Lim Isaak","key":"e_1_2_2_26_1","unstructured":"Isaak Lim, Alexander Dielen, Marcel Campen, and Leif Kobbelt. 2018. A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes. In European Conference on Computer Vision Workshops . 349--362."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.603"},{"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\/ICCVW.2015.112"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.01.001"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3144454"},{"key":"e_1_2_2_32_1","article-title":"Zoomout: Spectral upsampling for efficient shape correspondence","volume":"38","author":"Melzi Simone","year":"2019","unstructured":"Simone Melzi, Jing Ren, Emanuele Rodol\u00e0, Abhishek Sharma, Peter Wonka, and Maks Ovsjanikov. 2019. Zoomout: Spectral upsampling for efficient shape correspondence. ACM Trans. on Graphics (Proc. SIGGRAPH Asia) 38, 6 (2019), 155:1--155:14.","journal-title":"ACM Trans. on Graphics (Proc. SIGGRAPH Asia)"},{"key":"e_1_2_2_33_1","unstructured":"Anastasiia Mishchuk Dmytro Mishkin Filip Radenovic and Jiri Matas. 2017. Working hard to know your neighbor's margins: Local descriptor learning loss. In Advances in Neural Information Processing Systems. 4826--4837."},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185526"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2005.10.011"},{"volume-title":"Proc. of Symp. of Geometry Processing. 225--233","year":"2007","author":"Rustamov Raif M","key":"e_1_2_2_36_1","unstructured":"Raif M Rustamov. 2007. Laplace-Beltrami eigenfunctions for deformation invariant shape representation. In Proc. of Symp. of Geometry Processing. 225--233."},{"volume-title":"Proc. of Symp. of Geometry Processing. 109--116","year":"2007","author":"Sorkine Olga","key":"e_1_2_2_37_1","unstructured":"Olga Sorkine and Marc Alexa. 2007. As-rigid-as-possible surface modeling. In Proc. of Symp. of Geometry Processing. 109--116."},{"volume-title":"Vertex-frequency analysis of graph signals","author":"Stankovi\u0107 Ljubi\u0161a","key":"e_1_2_2_38_1","unstructured":"Ljubi\u0161a Stankovi\u0107 and Ervin Sejdi\u0107. 2019. Vertex-frequency analysis of graph signals. Springer."},{"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"},{"volume-title":"Feastnet: Feature-steered graph convolutions for 3d shape analysis","year":"2018","author":"Verma Nitika","key":"e_1_2_2_41_1","unstructured":"Nitika Verma, Edmond Boyer, and Jakob Verbeek. 2018. Feastnet: Feature-steered graph convolutions for 3d shape analysis. In IEEE Computer Vision and Pattern Recognition (CVPR). 2598--2606."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_1"},{"volume-title":"A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures","author":"Wang Yiqun","key":"e_1_2_2_43_1","unstructured":"Yiqun Wang, Jianwei Guo, Dong-Ming Yan, Kai Wang, and Xiaopeng Zhang. 2019a. A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures. In IEEE Computer Vision and Pattern Recognition (CVPR). 6231--6240."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2837115"},{"volume-title":"Dense human body correspondences using convolutional networks","author":"Wei Lingyu","key":"e_1_2_2_46_1","unstructured":"Lingyu Wei, Qixing Huang, Duygu Ceylan, Etienne Vouga, and Hao Li. 2016. Dense human body correspondences using convolutional networks. In IEEE Computer Vision and Pattern Recognition (CVPR). 1544--1553."},{"key":"e_1_2_2_47_1","unstructured":"Bingbing Xu Huawei Shen Qi Cao Yunqi Qiu and Xueqi Cheng. 2019. Graph Wavelet Neural Network. In ICLR (Poster)."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.2330574"},{"volume-title":"Surface feature detection and description with applications to mesh matching","author":"Zaharescu Andrei","key":"e_1_2_2_49_1","unstructured":"Andrei Zaharescu, Edmond Boyer, Kiran Varanasi, and Radu Horaud. 2009. Surface feature detection and description with applications to mesh matching. In IEEE Computer Vision and Pattern Recognition (CVPR). 373--380."},{"volume-title":"3DMatch: Learning local geometric descriptors from rgb-d reconstructions","author":"Zeng Andy","key":"e_1_2_2_50_1","unstructured":"Andy Zeng, Shuran Song, Matthias Nie\u00dfner, Matthew Fisher, Jianxiong Xiao, and Thomas Funkhouser. 2017. 3DMatch: Learning local geometric descriptors from rgb-d reconstructions. In IEEE Computer Vision and Pattern Recognition (CVPR). 199--208."},{"volume-title":"Black","year":"2017","author":"Zuffi Silvia","key":"e_1_2_2_51_1","unstructured":"Silvia Zuffi, Angjoo Kanazawa, David Jacobs, and Michael J. Black. 2017. 3D Menagerie: Modeling the 3D Shape and Pose of Animals. In IEEE Computer Vision and Pattern Recognition (CVPR). 6365--6373."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386569.3392443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:32:49Z","timestamp":1725496369000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386569.3392443"}},"subtitle":["descriptor learning using multiscale GCNs"],"short-title":[],"issued":{"date-parts":[[2020,8,12]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,8,31]]}},"alternative-id":["10.1145\/3386569.3392443"],"URL":"http:\/\/dx.doi.org\/10.1145\/3386569.3392443","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"subject":[],"published":{"date-parts":[[2020,8,12]]},"assertion":[{"value":"2020-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
