{"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/collecting-the-puzzle-pieces-disentangled","title":"Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures","arxiv_id":"2210.01887","date":"2022-10-04","proceeding":"ICCV 2023 1","authors":["Nannan Li","Kevin J. Shih","Bryan A. Plummer"],"abstract":"Human pose transfer synthesizes new view(s) of a person for a given pose. Recent work achieves this via self-reconstruction, which disentangles a person's pose and texture information by breaking the person down into parts, then recombines them for reconstruction. However, part-level disentanglement preserves some pose information that can create unwanted artifacts. In this paper, we propose Pose Transfer by Permuting Textures (PT$^2$), an approach for self-driven human pose transfer that disentangles pose from texture at the patch-level. Specifically, we remove pose from an input image by permuting image patches so only texture information remains. Then we reconstruct the input image by sampling from the permuted textures for patch-level disentanglement. To reduce noise and recover clothing shape information from the permuted patches, we employ encoders with multiple kernel sizes in a triple branch network. On DeepFashion and Market-1501, PT$^2$ reports significant gains on automatic metrics over other self-driven methods, and even outperforms some fully-supervised methods. A user study also reports images generated by our method are preferred in 68% of cases over self-driven approaches from prior work. Code is available at https://github.com/NannanLi999/pt_square.","url_abs":"https://arxiv.org/abs/2210.01887v3","url_pdf":"https://arxiv.org/pdf/2210.01887v3.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":"collecting-the-puzzle-pieces-disentangled","repo_url":"https://github.com/nannanli999/pt_square","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"pose-transfer","task_name":"Pose Transfer"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[{"method_slug":"branch-attention","method_name":"Branch attention"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}