{"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/a-fusion-approach-for-multi-frame-optical","title":"A Fusion Approach for Multi-Frame Optical Flow Estimation","arxiv_id":"1810.10066","date":"2018-10-23","proceeding":null,"authors":["Zhile Ren","Orazio Gallo","Deqing Sun","Ming-Hsuan Yang","Erik B. Sudderth","Jan Kautz"],"abstract":"To date, top-performing optical flow estimation methods only take pairs of\nconsecutive frames into account. While elegant and appealing, the idea of using\nmore than two frames has not yet produced state-of-the-art results. We present\na simple, yet effective fusion approach for multi-frame optical flow that\nbenefits from longer-term temporal cues. Our method first warps the optical\nflow from previous frames to the current, thereby yielding multiple plausible\nestimates. It then fuses the complementary information carried by these\nestimates into a new optical flow field. At the time of writing, our method\nranks first among published results in the MPI Sintel and KITTI 2015\nbenchmarks. Our models will be available on https://github.com/NVlabs/PWC-Net.","url_abs":"http://arxiv.org/abs/1810.10066v2","url_pdf":"http://arxiv.org/pdf/1810.10066v2.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":"a-fusion-approach-for-multi-frame-optical","repo_url":"https://github.com/NVlabs/PWC-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"a-fusion-approach-for-multi-frame-optical","repo_url":"https://github.com/kimwoojoo/edit_multiflow","is_official":0,"mentioned_in_paper":0,"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.10066","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}