{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T18:02:58Z","timestamp":1772042578932,"version":"3.50.1"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T00:00:00Z","timestamp":1606435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF grant","award":["IIS-1815070"],"award-info":[{"award-number":["IIS-1815070"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61825305, 61751311, 61572507, 61532003, 61622212"],"award-info":[{"award-number":["61825305, 61751311, 61572507, 61532003, 61622212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0102200, 2018YFB1305105"],"award-info":[{"award-number":["2018AAA0102200, 2018YFB1305105"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2020,12,31]]},"abstract":"<jats:p>We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.<\/jats:p>","DOI":"10.1145\/3414685.3417775","type":"journal-article","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T21:51:05Z","timestamp":1606513865000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["SymmetryNet"],"prefix":"10.1145","volume":"39","author":[{"given":"Yifei","family":"Shi","sequence":"first","affiliation":[{"name":"National University of Defense Technology"}]},{"given":"Junwen","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}]},{"given":"Hongjia","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}]},{"given":"Szymon","family":"Rusinkiewicz","sequence":"additional","affiliation":[{"name":"Princeton University"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}]}],"member":"320","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00272"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01410.x"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"e_1_2_2_4_1","volume-title":"et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012","author":"Chang Angel X","year":"2015","unstructured":"Angel X Chang , Thomas Funkhouser , Leonidas Guibas , Pat Hanrahan , Qixing Huang , Zimo Li , Silvio Savarese , Manolis Savva , Shuran Song , Hao Su , et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 , 2015 . Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386067"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593822"},{"key":"e_1_2_2_8_1","first-page":"226","volume-title":"KDD","volume":"96","author":"Ester Martin","year":"1996","unstructured":"Martin Ester , Hans-Peter Kriegel , J\u00f6rg Sander , Xiaowei Xu , A density-based algorithm for discovering clusters in large spatial databases with noise . In KDD , volume 96 , pages 226 -- 231 , 1996 . Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. In KDD, volume 96, pages 226--231, 1996."},{"key":"e_1_2_2_9_1","first-page":"1692","volume-title":"Proc. ICCV","author":"Funk Christopher","year":"2017","unstructured":"Christopher Funk , Seungkyu Lee , Martin R Oswald , Stavros Tsogkas , Wei Shen , Andrea Cohen , Sven Dickinson , and Yanxi Liu . 2017 iccv challenge: Detecting symmetry in the wild . In Proc. ICCV , pages 1692 -- 1701 , 2017. Christopher Funk, Seungkyu Lee, Martin R Oswald, Stavros Tsogkas, Wei Shen, Andrea Cohen, Sven Dickinson, and Yanxi Liu. 2017 iccv challenge: Detecting symmetry in the wild. In Proc. ICCV, pages 1692--1701, 2017."},{"key":"e_1_2_2_10_1","volume-title":"Prs-net: Planar reflective symmetry detection net for 3d models. arXiv preprint arXiv:1910.06511","author":"Gao Lin","year":"2019","unstructured":"Lin Gao , Ling-Xiao Zhang , Hsien-Yu Meng , Yi-Hui Ren , Yu-Kun Lai , and Leif Kobbelt . Prs-net: Planar reflective symmetry detection net for 3d models. arXiv preprint arXiv:1910.06511 , 2019 . Lin Gao, Ling-Xiao Zhang, Hsien-Yu Meng, Yi-Hui Ren, Yu-Kun Lai, and Leif Kobbelt. Prs-net: Planar reflective symmetry detection net for 3d models. arXiv preprint arXiv:1910.06511, 2019."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1057432.1057461"},{"key":"e_1_2_2_12_1","volume-title":"Matching rgb images to cad models for object pose estimation. arXiv preprint arXiv:1811.07249","author":"Georgakis Georgios","year":"2018","unstructured":"Georgios Georgakis , Srikrishna Karanam , Ziyan Wu , and Jana Kosecka . Matching rgb images to cad models for object pose estimation. arXiv preprint arXiv:1811.07249 , 2018 . Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, and Jana Kosecka. Matching rgb images to cad models for object pose estimation. arXiv preprint arXiv:1811.07249, 2018."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354005"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2679114"},{"key":"e_1_2_2_15_1","volume-title":"Learning local shape descriptors from part correspondences with multiview convolutional networks. ACM Transactions on Graphics (TOG), 37(1):1--14","author":"Huang Haibin","year":"2017","unstructured":"Haibin Huang , Evangelos Kalogerakis , Siddhartha Chaudhuri , Duygu Ceylan , Vladimir G Kim , and Ersin Yumer . Learning local shape descriptors from part correspondences with multiview convolutional networks. ACM Transactions on Graphics (TOG), 37(1):1--14 , 2017 . Haibin Huang, Evangelos Kalogerakis, Siddhartha Chaudhuri, Duygu Ceylan, Vladimir G Kim, and Ersin Yumer. Learning local shape descriptors from part correspondences with multiview convolutional networks. ACM Transactions on Graphics (TOG), 37(1):1--14, 2017."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.40"},{"key":"e_1_2_2_17_1","volume-title":"Blended intrinsic maps. ACM Transactions on Graphics (TOG), 30(4):1--12","author":"Kim Vladimir G","year":"2011","unstructured":"Vladimir G Kim , Yaron Lipman , and Thomas Funkhouser . Blended intrinsic maps. ACM Transactions on Graphics (TOG), 30(4):1--12 , 2011 . Vladimir G Kim, Yaron Lipman, and Thomas Funkhouser. Blended intrinsic maps. ACM Transactions on Graphics (TOG), 30(4):1--12, 2011."},{"key":"e_1_2_2_18_1","volume-title":"Proc. ICLR","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. Adam : A method for stochastic optimization . In Proc. ICLR , 2015 . Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Proc. ICLR, 2015."},{"key":"e_1_2_2_19_1","volume-title":"Real-time 6d object pose estimation on cpu. arXiv preprint arXiv:1811.08588","author":"Konishi Yoshinori","year":"2018","unstructured":"Yoshinori Konishi , Kosuke Hattori , and Manabu Hashimoto . Real-time 6d object pose estimation on cpu. arXiv preprint arXiv:1811.08588 , 2018 . Yoshinori Konishi, Kosuke Hattori, and Manabu Hashimoto. Real-time 6d object pose estimation on cpu. arXiv preprint arXiv:1811.08588, 2018."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8655(91)90039-O"},{"key":"e_1_2_2_21_1","volume-title":"The hungarian method for the assignment problem. Naval research logistics quarterly, 2(1--2):83--97","author":"Kuhn Harold W","year":"1955","unstructured":"Harold W Kuhn . The hungarian method for the assignment problem. Naval research logistics quarterly, 2(1--2):83--97 , 1955 . Harold W Kuhn. The hungarian method for the assignment problem. Naval research logistics quarterly, 2(1--2):83--97, 1955."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2669043.2669045"},{"key":"e_1_2_2_23_1","volume-title":"Grass: Generative recursive autoencoders for shape structures. ACM Transactions on Graphics (TOG), 36(4):1--14","author":"Li Jun","year":"2017","unstructured":"Jun Li , Kai Xu , Siddhartha Chaudhuri , Ersin Yumer , Hao Zhang , and Leonidas Guibas . Grass: Generative recursive autoencoders for shape structures. ACM Transactions on Graphics (TOG), 36(4):1--14 , 2017 . Jun Li, Kai Xu, Siddhartha Chaudhuri, Ersin Yumer, Hao Zhang, and Leonidas Guibas. Grass: Generative recursive autoencoders for shape structures. ACM Transactions on Graphics (TOG), 36(4):1--14, 2017."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778840"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6827"},{"key":"e_1_2_2_26_1","first-page":"537","volume-title":"Proc. CVPR","volume":"1","author":"Liu Yanxi","year":"2000","unstructured":"Yanxi Liu and Robert T Collins . A computational model for repeated pattern perception using frieze and wallpaper groups . In Proc. CVPR , volume 1 , pages 537 -- 544 . IEEE, 2000 . Yanxi Liu and Robert T Collins. A computational model for repeated pattern perception using frieze and wallpaper groups. In Proc. CVPR, volume 1, pages 537--544. IEEE, 2000."},{"key":"e_1_2_2_27_1","first-page":"2001","volume-title":"Proc. CVPR","volume":"1","author":"Liu Yanxi","unstructured":"Yanxi Liu and Robert T Collins . Skewed symmetry groups . In Proc. CVPR , volume 1 , pages I-I. IEEE, 2001 . Yanxi Liu and Robert T Collins. Skewed symmetry groups. In Proc. CVPR, volume 1, pages I-I. IEEE, 2001."},{"key":"e_1_2_2_28_1","volume-title":"Luc Van Gool, et al. Computational symmetry in computer vision and computer graphics. Foundations and Trends\u00ae in Computer Graphics and Vision, 5(1--2):1--195","author":"Liu Yanxi","year":"2010","unstructured":"Yanxi Liu , Hagit Hel-Or , Craig S Kaplan , Luc Van Gool, et al. Computational symmetry in computer vision and computer graphics. Foundations and Trends\u00ae in Computer Graphics and Vision, 5(1--2):1--195 , 2010 . Yanxi Liu, Hagit Hel-Or, Craig S Kaplan, Luc Van Gool, et al. Computational symmetry in computer vision and computer graphics. Foundations and Trends\u00ae in Computer Graphics and Vision, 5(1--2):1--195, 2010."},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.23119"},{"key":"e_1_2_2_30_1","volume-title":"Accurate detection of symmetries in 3d shapes. ACM Transactions on Graphics (TOG), 25(2): 439--464","author":"Martinet Aur\u00e9lien","year":"2006","unstructured":"Aur\u00e9lien Martinet , Cyril Soler , Nicolas Holzschuch , and Fran\u00e7ois X Sillion . Accurate detection of symmetries in 3d shapes. ACM Transactions on Graphics (TOG), 25(2): 439--464 , 2006 . Aur\u00e9lien Martinet, Cyril Soler, Nicolas Holzschuch, and Fran\u00e7ois X Sillion. Accurate detection of symmetries in 3d shapes. ACM Transactions on Graphics (TOG), 25(2): 439--464, 2006."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1179352.1141924"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12010"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8655(91)90022-E"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01273.x"},{"key":"e_1_2_2_35_1","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , : An imperative style, high-performance deep learning library . In Advances in Neural Information Processing Systems , pages 8024 -- 8035 , 2019 . Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, pages 8024--8035, 2019."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"e_1_2_2_37_1","volume-title":"July","author":"Podolak Joshua","year":"2006","unstructured":"Joshua Podolak , Philip Shilane , Aleksey Golovinskiy , Szymon Rusinkiewicz , and Thomas Funkhouser . A planar-reflective symmetry transform for 3D shapes. ACM Transactions on Graphics (TOG), 25(3) , July 2006 . Joshua Podolak, Philip Shilane, Aleksey Golovinskiy, Szymon Rusinkiewicz, and Thomas Funkhouser. A planar-reflective symmetry transform for 3D shapes. ACM Transactions on Graphics (TOG), 25(3), July 2006."},{"key":"e_1_2_2_38_1","first-page":"652","volume-title":"Proc. CVPR","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi , Hao Su , Kaichun Mo , and Leonidas J Guibas . Pointnet : Deep learning on point sets for 3d classification and segmentation . In Proc. CVPR , pages 652 -- 660 , 2017 . Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proc. CVPR, pages 652--660, 2017."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409181"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0320-3"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.10.015"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.31"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.192"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_4"},{"key":"e_1_2_2_45_1","first-page":"1681","volume-title":"Computer Graphics Forum","volume":"30","author":"Kaick Oliver Van","year":"2011","unstructured":"Oliver Van Kaick , Hao Zhang , Ghassan Hamarneh , and Daniel Cohen-Or . A survey on shape correspondence . In Computer Graphics Forum , volume 30 , pages 1681 -- 1707 , 2011 . Oliver Van Kaick, Hao Zhang, Ghassan Hamarneh, and Daniel Cohen-Or. A survey on shape correspondence. In Computer Graphics Forum, volume 30, pages 1681--1707, 2011."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01885.x"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.171"},{"key":"e_1_2_2_50_1","volume-title":"Partial intrinsic reflectional symmetry of 3d shapes. ACM Transactions on Graphics (TOG), 28(5):1--10","author":"Xu Kai","year":"2009","unstructured":"Kai Xu , Hao Zhang , Andrea Tagliasacchi , Ligang Liu , Guo Li , Min Meng , and Yueshan Xiong . Partial intrinsic reflectional symmetry of 3d shapes. ACM Transactions on Graphics (TOG), 28(5):1--10 , 2009 . Kai Xu, Hao Zhang, Andrea Tagliasacchi, Ligang Liu, Guo Li, Min Meng, and Yueshan Xiong. Partial intrinsic reflectional symmetry of 3d shapes. ACM Transactions on Graphics (TOG), 28(5):1--10, 2009."},{"key":"e_1_2_2_51_1","first-page":"206","volume-title":"Proc. CVPR","author":"Yang Yaoqing","year":"2018","unstructured":"Yaoqing Yang , Chen Feng , Yiru Shen , and Dong Tian . Foldingnet : Point cloud autoencoder via deep grid deformation . In Proc. CVPR , pages 206 -- 215 , 2018 . Yaoqing Yang, Chen Feng, Yiru Shen, and Dong Tian. Foldingnet: Point cloud autoencoder via deep grid deformation. In Proc. CVPR, pages 206--215, 2018."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(99)00138-5"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00972"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-55426-2_100"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3414685.3417775","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3414685.3417775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:03:14Z","timestamp":1750197794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3414685.3417775"}},"subtitle":["learning to predict reflectional and rotational symmetries of 3D shapes from single-view RGB-D images"],"short-title":[],"issued":{"date-parts":[[2020,11,27]]},"references-count":55,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,12,31]]}},"alternative-id":["10.1145\/3414685.3417775"],"URL":"https:\/\/doi.org\/10.1145\/3414685.3417775","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,27]]},"assertion":[{"value":"2020-11-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}