{"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/recycle-gan-unsupervised-video-retargeting","title":"Recycle-GAN: Unsupervised Video Retargeting","arxiv_id":"1808.05174","date":"2018-08-15","proceeding":"ECCV 2018 9","authors":["Aayush Bansal","Shugao Ma","Deva Ramanan","Yaser Sheikh"],"abstract":"We introduce a data-driven approach for unsupervised video retargeting that\ntranslates content from one domain to another while preserving the style native\nto a domain, i.e., if contents of John Oliver's speech were to be transferred\nto Stephen Colbert, then the generated content/speech should be in Stephen\nColbert's style. Our approach combines both spatial and temporal information\nalong with adversarial losses for content translation and style preservation.\nIn this work, we first study the advantages of using spatiotemporal constraints\nover spatial constraints for effective retargeting. We then demonstrate the\nproposed approach for the problems where information in both space and time\nmatters such as face-to-face translation, flower-to-flower, wind and cloud\nsynthesis, sunrise and sunset.","url_abs":"http://arxiv.org/abs/1808.05174v1","url_pdf":"http://arxiv.org/pdf/1808.05174v1.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":"recycle-gan-unsupervised-video-retargeting","repo_url":"https://github.com/aayushbansal/Recycle-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"face-to-face-translation","task_name":"Face to Face Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.05174","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}