{"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/optical-flow-requires-multiple-strategies-but","title":"Optical Flow Requires Multiple Strategies (but only one network)","arxiv_id":"1611.05607","date":"2016-11-17","proceeding":"CVPR 2017 7","authors":["Tal Schuster","Lior Wolf","David Gadot"],"abstract":"We show that the matching problem that underlies optical flow requires\nmultiple strategies, depending on the amount of image motion and other factors.\nWe then study the implications of this observation on training a deep neural\nnetwork for representing image patches in the context of descriptor based\noptical flow. We propose a metric learning method, which selects suitable\nnegative samples based on the nature of the true match. This type of training\nproduces a network that displays multiple strategies depending on the input and\nleads to state of the art results on the KITTI 2012 and KITTI 2015 optical flow\nbenchmarks.","url_abs":"http://arxiv.org/abs/1611.05607v3","url_pdf":"http://arxiv.org/pdf/1611.05607v3.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":"optical-flow-requires-multiple-strategies-but","repo_url":"https://github.com/DediGadot/PatchBatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}