{"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/graph-cut-ransac","title":"Graph-Cut RANSAC","arxiv_id":"1706.00984","date":"2017-06-03","proceeding":"CVPR 2018 6","authors":["Daniel Barath","Jiri Matas"],"abstract":"A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in\nshort, is introduced. To separate inliers and outliers, it runs the graph-cut\nalgorithm in the local optimization (LO) step which is applied when a\nso-far-the-best model is found. The proposed LO step is conceptually simple,\neasy to implement, globally optimal and efficient. GC-RANSAC is shown\nexperimentally, both on synthesized tests and real image pairs, to be more\ngeometrically accurate than state-of-the-art methods on a range of problems,\ne.g. line fitting, homography, affine transformation, fundamental and essential\nmatrix estimation. It runs in real-time for many problems at a speed\napproximately equal to that of the less accurate alternatives (in milliseconds\non standard CPU).","url_abs":"http://arxiv.org/abs/1706.00984v2","url_pdf":"http://arxiv.org/pdf/1706.00984v2.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":"graph-cut-ransac","repo_url":"https://github.com/danini/graph-cut-ransac","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"CPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00984","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}