{"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/mft-long-term-tracking-of-every-pixel","title":"MFT: Long-Term Tracking of Every Pixel","arxiv_id":"2305.12998","date":"2023-05-22","proceeding":null,"authors":["Michal Neoral","Jonáš Šerých","Jiří Matas"],"abstract":"We propose MFT -- Multi-Flow dense Tracker -- a novel method for dense, pixel-level, long-term tracking. The approach exploits optical flows estimated not only between consecutive frames, but also for pairs of frames at logarithmically spaced intervals. It selects the most reliable sequence of flows on the basis of estimates of its geometric accuracy and the probability of occlusion, both provided by a pre-trained CNN. We show that MFT achieves competitive performance on the TAP-Vid benchmark, outperforming baselines by a significant margin, and tracking densely orders of magnitude faster than the state-of-the-art point-tracking methods. The method is insensitive to medium-length occlusions and it is robustified by estimating flow with respect to the reference frame, which reduces drift.","url_abs":"https://arxiv.org/abs/2305.12998v2","url_pdf":"https://arxiv.org/pdf/2305.12998v2.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":"mft-long-term-tracking-of-every-pixel","repo_url":"https://github.com/serycjon/MFT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"point-tracking","task_name":"Point Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.12998","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}