{"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/video-enhancement-with-task-oriented-flow","title":"Video Enhancement with Task-Oriented Flow","arxiv_id":"1711.09078","date":"2017-11-24","proceeding":null,"authors":["Tianfan Xue","Baian Chen","Jiajun Wu","Donglai Wei","William T. Freeman"],"abstract":"Many video enhancement algorithms rely on optical flow to register frames in a video sequence. Precise flow estimation is however intractable; and optical flow itself is often a sub-optimal representation for particular video processing tasks. In this paper, we propose task-oriented flow (TOFlow), a motion representation learned in a self-supervised, task-specific manner. We design a neural network with a trainable motion estimation component and a video processing component, and train them jointly to learn the task-oriented flow. For evaluation, we build Vimeo-90K, a large-scale, high-quality video dataset for low-level video processing. TOFlow outperforms traditional optical flow on standard benchmarks as well as our Vimeo-90K dataset in three video processing tasks: frame interpolation, video denoising/deblocking, and video super-resolution.","url_abs":"https://arxiv.org/abs/1711.09078v3","url_pdf":"https://arxiv.org/pdf/1711.09078v3.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":"video-enhancement-with-task-oriented-flow","repo_url":"https://github.com/Coldog2333/pytoflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"video-enhancement-with-task-oriented-flow","repo_url":"https://github.com/jcao216/DAIN_Modified","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"video-enhancement-with-task-oriented-flow","repo_url":"https://github.com/laomao0/BIN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"video-enhancement-with-task-oriented-flow","repo_url":"https://github.com/anchen1011/toflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"motion-estimation","task_name":"Motion Estimation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-denoising","task_name":"Video Denoising"},{"task_slug":"video-enhancement","task_name":"Video Enhancement"},{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"},{"task_slug":"video-super-resolution","task_name":"Video Super-Resolution"}],"methods":[],"datasets_introduced":[{"slug":"vimeo90k-1","name":"Vimeo90K","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-frame-interpolation-on-middlebury","task":"Video Frame Interpolation","dataset":"Middlebury","model":"ToFlow","rank_in_archive_order":7,"of":11,"metrics":{"Interpolation Error":"5.49"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-vimeo90k","task":"Video Frame Interpolation","dataset":"Vimeo90K","model":"ToFlow","rank_in_archive_order":23,"of":23,"metrics":{"PSNR":"33.73"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling-1","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling - BD degradation","model":"TOFlow","rank_in_archive_order":18,"of":18,"metrics":{"PSNR":"25.85","SSIM":"0.7659"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09078","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}