{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:17:06Z","timestamp":1790709426153,"version":"4.1.0"},"reference-count":42,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T00:00:00Z","timestamp":1610409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Descriptors play an important role in point cloud registration. The current state-of-the-art resorts to the high regression capability of deep learning. However, recent deep learning-based descriptors require different levels of annotation and selection of patches, which make the model hard to migrate to new scenarios. In this work, we learn local registration descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. Thus, the whole training requires no manual annotation and manual selection of patches. In addition, we propose to involve keypoint sampling into the pipeline, which further improves the performance of our model. Our experiments demonstrate the capability of our self-supervised local descriptor to achieve even better performance than the supervised model, while being easier to train and requiring no data labeling.<\/jats:p>","DOI":"10.3390\/s21020486","type":"journal-article","created":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T20:11:31Z","timestamp":1610482291000},"page":"486","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Self-Supervised Point Set Local Descriptors for Point Cloud Registration"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6147-4846","authenticated-orcid":false,"given":"Yijun","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Information Science &amp; Technology, ShanghaiTech University, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-4913","authenticated-orcid":false,"given":"Dorit","family":"Borrmann","sequence":"additional","affiliation":[{"name":"Informatics VII\u2014Robotics and Telematics, Julius-Maximilians-University W\u00fcrzburg, 97070 W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6728-0997","authenticated-orcid":false,"given":"Jiawei","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Information Science &amp; Technology, ShanghaiTech University, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7237-988X","authenticated-orcid":false,"given":"Yuexin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Information Science &amp; Technology, ShanghaiTech University, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3870-783X","authenticated-orcid":false,"given":"Andreas","family":"N\u00fcchter","sequence":"additional","affiliation":[{"name":"Informatics VII\u2014Robotics and Telematics, Julius-Maximilians-University W\u00fcrzburg, 97070 W\u00fcrzburg, Germany"},{"name":"School of Information Science &amp; Technology, ShanghaiTech University, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2879-1636","authenticated-orcid":false,"given":"S\u00f6ren","family":"Schwertfeger","sequence":"additional","affiliation":[{"name":"School of Information Science &amp; Technology, ShanghaiTech University, Shanghai 201210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1109\/MRA.2006.1678144","article-title":"Simultaneous localization and mapping: Part I","volume":"13","author":"Bailey","year":"2006","journal-title":"IEEE Robot. Autom. Mag."},{"key":"ref_2","first-page":"699","article-title":"6D SLAM \u2013 3D Mapping Outdoor Environments","volume":"24","author":"Lingemann","year":"2007","journal-title":"J. Field Robot. (JFR) Spec. Issue Quant. Perform. Eval. Robot. Intell. Syst."},{"key":"ref_3","first-page":"892","article-title":"3D Mapping with Time-of-Flight Cameras","volume":"26","author":"May","year":"2009","journal-title":"J. Field Robot. (JFR) Spec. Issue-Three-Dimens. Mapp."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, H., and Hartley, R. (2007, January 14\u201320). The 3D-3D registration problem revisited. Proceedings of the 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil.","DOI":"10.1109\/ICCV.2007.4409077"},{"key":"ref_5","unstructured":"Bellekens, B., Spruyt, V., Berkvens, R., and Weyn, M. (2014, January 24\u201328). A survey of rigid 3D pointcloud registration algorithms. Proceedings of the AMBIENT 2014: The Fourth International Conference on Ambient Computing, Applications, Services and Technologies, Rome, Italy."},{"key":"ref_6","unstructured":"Marden, S., and Guivant, J. (2012, January 3\u20135). Improving the performance of ICP for real-time applications using an approximate nearest neighbour search. Proceedings of the Australasian Conference on Robotics and Automation, Wellington, New Zealand."},{"key":"ref_7","first-page":"586","article-title":"Method for registration of 3-D shapes. Sensor Fusion IV: Control Paradigms and Data Structures","volume":"1611","author":"Besl","year":"1992","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Fantoni, S., Castellani, U., and Fusiello, A. (2012, January 13\u201315). Accurate and automatic alignment of range surfaces. Proceedings of the 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, Zurich, Switzerland.","DOI":"10.1109\/3DIMPVT.2012.63"},{"key":"ref_9","first-page":"435","article-title":"Generalized-icp","volume":"2","author":"Segal","year":"2009","journal-title":"Robot. Sci. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Rusu, R.B., Blodow, N., and Beetz, M. (2009, January 12\u201317). Fast point feature histograms (FPFH) for 3D registration. Proceedings of the 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan.","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"ref_11","unstructured":"Tsin, Y., and Kanade, T. (2014, January 11\u201314). A correlation-based approach to robust point set registration. Proceedings of the European Conference on Computer Visio, Prague, Czech Republic."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2262","DOI":"10.1109\/TPAMI.2010.46","article-title":"Point set registration: Coherent point drift","volume":"32","author":"Myronenko","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"209","DOI":"10.2197\/ipsjtcva.1.209","article-title":"A fast registration method using IP and its application to ultrasound image registration","volume":"1","author":"Zheng","year":"2009","journal-title":"IPSJ Trans. Comput. Vis. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rusu, R.B., Marton, Z.C., Blodow, N., and Beetz, M. (2008, January 17\u201320). Learning informative point classes for the acquisition of object model maps. Proceedings of the 2008 10th International Conference on Control, Automation, Robotics and Vision, Hanoi, Vietnam.","DOI":"10.1109\/ICARCV.2008.4795593"},{"key":"ref_15","unstructured":"Huber, D.F., and Hebert, M. (2002). Automatic Three-Dimensional Modeling from Reality. [Ph.D. Thesis, Carnegie Mellon University]."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tombari, F., Salti, S., and Di Stefano, L. (2010, January 25\u201329). Unique shape context for 3D data description. Proceedings of the ACM workshop on 3D Object Retrieval, Firenze, Italy.","DOI":"10.1145\/1877808.1877821"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.isprsjprs.2007.05.005","article-title":"Keypoint based autonomous registration of terrestrial laser point-clouds","volume":"63","author":"Barnea","year":"2008","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Steder, B., Grisetti, G., and Burgard, W. (2010, January 3\u20138). Robust place recognition for 3D range data based on point features. Proceedings of the 2010 IEEE International Conference on Robotics and Automation, Anchorage, Alaska.","DOI":"10.1109\/ROBOT.2010.5509401"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Flint, A., Dick, A., and Van Den Hengel, A. (2007, January 3\u20135). Thrift: Local 3d structure recognition. Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007), Glenelg, Australia.","DOI":"10.1109\/DICTA.2007.4426794"},{"key":"ref_20","unstructured":"Wu, C., Clipp, B., Li, X., Frahm, J.M., and Pollefeys, M. (2008, January 23\u201328). 3D model matching with viewpoint-invariant patches (VIP). Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zeng, A., Song, S., Nie\u00dfner, M., Fisher, M., Xiao, J., and Funkhouser, T. (2017, January 21\u201326). 3dmatch: Learning local geometric descriptors from rgb-d reconstructions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gojcic, Z., Zhou, C., Wegner, J.D., and Wieser, A. (2019, January 15\u201320). The perfect match: 3d point cloud matching with smoothed densities. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00569"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Deng, H., Birdal, T., and Ilic, S. (2018, January 18\u201323). Ppfnet: Global context aware local features for robust 3d point matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00028"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Deng, H., Birdal, T., and Ilic, S. (2018, January 8\u201314). Ppf-foldnet: Unsupervised learning of rotation invariant 3d local descriptors. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01228-1_37"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Bai, X., Luo, Z., Zhou, L., Fu, H., Quan, L., and Tai, C.L. (2020, January 13\u201319). D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00639"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yew, Z.J., and Lee, G.H. (2018, January 8\u201314). 3DFeat-Net: Weakly supervised local 3D features for point cloud registration. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01267-0_37"},{"key":"ref_27","unstructured":"Lu, F., Chen, G., Liu, Y., Qu, Z., and Knoll, A. (2020). RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor. arXiv."},{"key":"ref_28","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4\u20139). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/0278364916679498","article-title":"1 year, 1000 km: The Oxford RobotCar dataset","volume":"36","author":"Maddern","year":"2017","journal-title":"Int. J. Robot. Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16\u201321). Are we ready for autonomous driving? The kitti vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yang, H., Shi, J., and Carlone, L. (2020). TEASER: Fast and Certifiable Point Cloud Registration. IEEE Trans. Robot.","DOI":"10.1109\/TRO.2020.3033695"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.isprsjprs.2020.11.014","article-title":"Robust global registration of point clouds by closed-form solution in the frequency domain","volume":"171","author":"Huang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"ref_33","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA."},{"key":"ref_34","unstructured":"Li, J., and Lee, G.H. (November, January 27). Usip: Unsupervised stable interest point detection from 3d point clouds. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_35","unstructured":"Fleuret, F., and Sahbi, H. (, January October). Scale-invariance of support vector machines based on the triangular kernel. Proceedings of the 3rd International Workshop on Statistical and Computational Theories of Vision, Nice, France."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/TPAMI.1987.4767965","article-title":"Least Square Fitting of Two 3-D Point Sets","volume":"9","author":"Arun","year":"1987","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_37","first-page":"52","article-title":"Least-squares rigid motion using svd","volume":"120","author":"Sorkine","year":"2009","journal-title":"Tech. Notes"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1115\/1.2735640","article-title":"A distance metric for finite sets of rigid-body displacements via the polar decomposition","volume":"129","author":"Larochelle","year":"2007","journal-title":"J. Mech. Des."},{"key":"ref_39","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), Savannah, GA, USA."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"J\u00e4remo Lawin, F., Danelljan, M., Shahbaz Khan, F., Forss\u00e9n, P.E., and Felsberg, M. (2018, January 18\u201323). Density adaptive point set registration. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00403"},{"key":"ref_41","unstructured":"Cignoni, P., Callieri, M., Corsini, M., Dellepiane, M., Ganovelli, F., and Ranzuglia, G. (2008, January 2\u20134). Meshlab: An open-source mesh processing tool. Proceedings of the Eurographics ITALIAN Chapter Conference, Salerno, Italy."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Rusu, R.B., and Cousins, S. (2011, January 9\u201313). 3d is here: Point cloud library (pcl). Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, China.","DOI":"10.1109\/ICRA.2011.5980567"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/2\/486\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:10:03Z","timestamp":1760159403000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/2\/486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,12]]},"references-count":42,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["s21020486"],"URL":"https:\/\/doi.org\/10.3390\/s21020486","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,12]]}}}