{"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/learning-energy-based-inpainting-for-optical","title":"Learning Energy Based Inpainting for Optical Flow","arxiv_id":"1811.03721","date":"2018-11-09","proceeding":null,"authors":["Christoph Vogel","Patrick Knöbelreiter","Thomas Pock"],"abstract":"Modern optical flow methods are often composed of a cascade of many\nindependent steps or formulated as a black box neural network that is hard to\ninterpret and analyze. In this work we seek for a plain, interpretable, but\nlearnable solution. We propose a novel inpainting based algorithm that\napproaches the problem in three steps: feature selection and matching,\nselection of supporting points and energy based inpainting. To facilitate the\ninference we propose an optimization layer that allows to backpropagate through\n10K iterations of a first-order method without any numerical or memory\nproblems. Compared to recent state-of-the-art networks, our modular CNN is very\nlightweight and competitive with other, more involved, inpainting based\nmethods.","url_abs":"http://arxiv.org/abs/1811.03721v1","url_pdf":"http://arxiv.org/pdf/1811.03721v1.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":"learning-energy-based-inpainting-for-optical","repo_url":"https://github.com/vogechri/CustomNetworkLayers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}