{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/go-icp-a-globally-optimal-solution-to-3d-icp","title":"Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration","arxiv_id":"1605.03344","date":"2016-05-11","proceeding":null,"authors":["Jiaolong Yang","Hongdong Li","Dylan Campbell","Yunde Jia"],"abstract":"The Iterative Closest Point (ICP) algorithm is one of the most widely used\nmethods for point-set registration. However, being based on local iterative\noptimization, ICP is known to be susceptible to local minima. Its performance\ncritically relies on the quality of the initialization and only local\noptimality is guaranteed. This paper presents the first globally optimal\nalgorithm, named Go-ICP, for Euclidean (rigid) registration of two 3D\npoint-sets under the L2 error metric defined in ICP. The Go-ICP method is based\non a branch-and-bound (BnB) scheme that searches the entire 3D motion space\nSE(3). By exploiting the special structure of SE(3) geometry, we derive novel\nupper and lower bounds for the registration error function. Local ICP is\nintegrated into the BnB scheme, which speeds up the new method while\nguaranteeing global optimality. We also discuss extensions, addressing the\nissue of outlier robustness. The evaluation demonstrates that the proposed\nmethod is able to produce reliable registration results regardless of the\ninitialization. Go-ICP can be applied in scenarios where an optimal solution is\ndesirable or where a good initialization is not always available.","url_abs":"http://arxiv.org/abs/1605.03344v1","url_pdf":"http://arxiv.org/pdf/1605.03344v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-to-point-cloud-registration","task_name":"Image to Point Cloud Registration"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-at-least-1","task":"Point Cloud Registration","dataset":"3DMatch (at least 30% overlapped - FCGF setting)","model":"Go-ICP","rank_in_archive_order":9,"of":14,"metrics":{"Recall (0.3m, 15 degrees)":"22.9"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-eth-trained-on","task":"Point Cloud Registration","dataset":"ETH (trained on 3DMatch)","model":"GO-ICP","rank_in_archive_order":20,"of":20,"metrics":{"Recall (30cm, 5 degrees)":"1.54"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-e","task":"Point Cloud Registration","dataset":"FP-O-E","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-h","task":"Point Cloud Registration","dataset":"FP-O-H","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-m","task":"Point Cloud Registration","dataset":"FP-O-M","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-e","task":"Point Cloud Registration","dataset":"FP-R-E","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-h","task":"Point Cloud Registration","dataset":"FP-R-H","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-m","task":"Point Cloud Registration","dataset":"FP-R-M","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"1.87","RTE (cm)":"2.71","Recall (3cm, 10 degrees)":"0.06"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-e","task":"Point Cloud Registration","dataset":"FP-T-E","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-h","task":"Point Cloud Registration","dataset":"FP-T-H","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-m","task":"Point Cloud Registration","dataset":"FP-T-M","model":"GO-ICP","rank_in_archive_order":6,"of":6,"metrics":{"RRE (degrees)":"-","RTE (cm)":"-","Recall (3cm, 10 degrees)":"0.00"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.03344","atlas_url":"https://app.syntology.ai/?focus=1605.03344","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}