{"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/scopeflow-dynamic-scene-scoping-for-optical","title":"ScopeFlow: Dynamic Scene Scoping for Optical Flow","arxiv_id":"2002.10770","date":"2020-02-25","proceeding":"CVPR 2020 6","authors":["Aviram Bar-Haim","Lior Wolf"],"abstract":"We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling challenging data that exists in the current training protocol, and improving the sampling process. In addition, we find that both regularization and augmentation should decrease during the training protocol. Using an existing low parameters architecture, the method is ranked first on the MPI Sintel benchmark among all other methods, improving the best two frames method accuracy by more than 10%. The method also surpasses all similar architecture variants by more than 12% and 19.7% on the KITTI benchmarks, achieving the lowest Average End-Point Error on KITTI2012 among two-frame methods, without using extra datasets.","url_abs":"https://arxiv.org/abs/2002.10770v2","url_pdf":"https://arxiv.org/pdf/2002.10770v2.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":"scopeflow-dynamic-scene-scoping-for-optical","repo_url":"https://github.com/avirambh/ScopeFlow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset":"Sintel-clean","model":"ScopeFlow","rank_in_archive_order":21,"of":29,"metrics":{"Average End-Point Error":"3.592"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final","task":"Optical Flow Estimation","dataset":"Sintel-final","model":"ScopeFlow","rank_in_archive_order":13,"of":28,"metrics":{"Average End-Point Error":"4.098"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.10770","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}