{"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/sdrsac-semidefinite-based-randomized-approach","title":"SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences","arxiv_id":"1904.03483","date":"2019-04-06","proceeding":null,"authors":["Huu Le","Thanh-Toan Do","Tuan Hoang","Ngai-Man Cheung"],"abstract":"This paper presents a novel randomized algorithm for robust point cloud\nregistration without correspondences. Most existing registration approaches\nrequire a set of putative correspondences obtained by extracting invariant\ndescriptors. However, such descriptors could become unreliable in noisy and\ncontaminated settings. In these settings, methods that directly handle input\npoint sets are preferable. Without correspondences, however, conventional\nrandomized techniques require a very large number of samples in order to reach\nsatisfactory solutions. In this paper, we propose a novel approach to address\nthis problem. In particular, our work enables the use of randomized methods for\npoint cloud registration without the need of putative correspondences. By\nconsidering point cloud alignment as a special instance of graph matching and\nemploying an efficient semi-definite relaxation, we propose a novel sampling\nmechanism, in which the size of the sampled subsets can be larger-than-minimal.\nOur tight relaxation scheme enables fast rejection of the outliers in the\nsampled sets, resulting in high-quality hypotheses. We conduct extensive\nexperiments to demonstrate that our approach outperforms other state-of-the-art\nmethods. Importantly, our proposed method serves as a generic framework which\ncan be extended to problems with known correspondences.","url_abs":"http://arxiv.org/abs/1904.03483v2","url_pdf":"http://arxiv.org/pdf/1904.03483v2.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":[{"paper_slug":"sdrsac-semidefinite-based-randomized-approach","repo_url":"https://github.com/intellhave/SDRSAC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03483","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}