{"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/faldoi-a-new-minimization-strategy-for-large","title":"FALDOI: A new minimization strategy for large displacement variational optical flow","arxiv_id":"1602.08960","date":"2016-02-29","proceeding":null,"authors":["Roberto P. Palomares","Enric Meinhardt-Llopis","Coloma Ballester","Gloria Haro"],"abstract":"We propose a large displacement optical flow method that introduces a new\nstrategy to compute a good local minimum of any optical flow energy functional.\nThe method requires a given set of discrete matches, which can be extremely\nsparse, and an energy functional which locally guides the interpolation from\nthose matches. In particular, the matches are used to guide a structured\ncoordinate-descent of the energy functional around these keypoints. It results\nin a two-step minimization method at the finest scale which is very robust to\nthe inevitable outliers of the sparse matcher and able to capture large\ndisplacements of small objects. Its benefits over other variational methods\nthat also rely on a set of sparse matches are its robustness against very few\nmatches, high levels of noise and outliers. We validate our proposal using\nseveral optical flow variational models. The results consistently outperform\nthe coarse-to-fine approaches and achieve good qualitative and quantitative\nperformance on the standard optical flow benchmarks.","url_abs":"http://arxiv.org/abs/1602.08960v3","url_pdf":"http://arxiv.org/pdf/1602.08960v3.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":"faldoi-a-new-minimization-strategy-for-large","repo_url":"https://github.com/fperezgamonal/faldoi-ipol","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}