{"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/parser-free-virtual-try-on-via-distilling","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","arxiv_id":"2103.04559","date":"2021-03-08","proceeding":"CVPR 2021 1","authors":["Yuying Ge","Yibing Song","Ruimao Zhang","Chongjian Ge","Wei Liu","Ping Luo"],"abstract":"Image virtual try-on aims to fit a garment image (target clothes) to a person image. Prior methods are heavily based on human parsing. However, slightly-wrong segmentation results would lead to unrealistic try-on images with large artifacts. Inaccurate parsing misleads parser-based methods to produce visually unrealistic results where artifacts usually occur. A recent pioneering work employed knowledge distillation to reduce the dependency of human parsing, where the try-on images produced by a parser-based method are used as supervisions to train a \"student\" network without relying on segmentation, making the student mimic the try-on ability of the parser-based model. However, the image quality of the student is bounded by the parser-based model. To address this problem, we propose a novel approach, \"teacher-tutor-student\" knowledge distillation, which is able to produce highly photo-realistic images without human parsing, possessing several appealing advantages compared to prior arts. (1) Unlike existing work, our approach treats the fake images produced by the parser-based method as \"tutor knowledge\", where the artifacts can be corrected by real \"teacher knowledge\", which is extracted from the real person images in a self-supervised way. (2) Other than using real images as supervisions, we formulate knowledge distillation in the try-on problem as distilling the appearance flows between the person image and the garment image, enabling us to find accurate dense correspondences between them to produce high-quality results. (3) Extensive evaluations show large superiority of our method (see Fig. 1).","url_abs":"https://arxiv.org/abs/2103.04559v2","url_pdf":"https://arxiv.org/pdf/2103.04559v2.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":"parser-free-virtual-try-on-via-distilling","repo_url":"https://github.com/geyuying/PF-AFN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"parser-free-virtual-try-on-via-distilling","repo_url":"https://github.com/KiseKloset/DM-VTON","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"human-parsing","task_name":"Human Parsing"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"virtual-try-on","task_name":"Virtual Try-on"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"teacher-tutor-student-knowledge-distillation","method_name":"Teacher-Tutor-Student Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"teacher-tutor-student-knowledge-distillation","name":"Teacher-Tutor-Student Knowledge Distillation","full_name":"Teacher-Tutor-Student Knowledge Distillation"}],"results":[{"leaderboard":"/sota/virtual-try-on-on-mpv","task":"Virtual Try-on","dataset":"MPV","model":"PF-AFN","rank_in_archive_order":1,"of":2,"metrics":{"FID":"6.429"},"uses_additional_data":false},{"leaderboard":"/sota/virtual-try-on-on-viton","task":"Virtual Try-on","dataset":"VITON","model":"PF-AFN","rank_in_archive_order":2,"of":10,"metrics":{"FID":"10.09"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.04559","atlas_url":"https://app.syntology.ai/?focus=2103.04559","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}