{"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/cyclegan-face-off","title":"CycleGAN Face-off","arxiv_id":"1712.03451","date":"2017-12-09","proceeding":null,"authors":["Xiaohan Jin","Ye Qi","Shangxuan Wu"],"abstract":"Face-off is an interesting case of style transfer where the facial\nexpressions and attributes of one person could be fully transformed to another\nface. We are interested in the unsupervised training process which only\nrequires two sequences of unaligned video frames from each person and learns\nwhat shared attributes to extract automatically. In this project, we explored\nvarious improvements for adversarial training (i.e. CycleGAN[Zhu et al., 2017])\nto capture details in facial expressions and head poses and thus generate\ntransformation videos of higher consistency and stability.","url_abs":"http://arxiv.org/abs/1712.03451v5","url_pdf":"http://arxiv.org/pdf/1712.03451v5.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":"cyclegan-face-off","repo_url":"https://github.com/ShangxuanWu/CycleGAN-Face-off","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}