{"url":"/sota/pose-transfer-on-deep-fashion","task":{"name":"Pose Transfer","url":"/task/pose-transfer","note":null},"dataset":{"name":"Deep-Fashion","url":"/dataset/deepfashion"},"category":"Computer Vision","categories":["Computer Vision","Medical","Miscellaneous","Natural Language Processing"],"category_note":null,"description":"Striptease","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["SSIM","IS","FID","DS","PCKh","LPIPS","Retrieval Top10 Recall"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"SSIM":"higher","IS":null,"FID":"lower","DS":null,"PCKh":null,"LPIPS":null,"Retrieval Top10 Recall":"higher"}},"counts":{"rows":12,"rows_with_code":12,"rows_with_paper_page":12,"rows_dated":12,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DiOr","metrics":{"SSIM":"0.806"},"uses_additional_data":false,"paper_date":"2021-04-14","paper":"/paper/dressing-in-order-recurrent-person-image","paper_url":"https://arxiv.org/abs/2104.07021v3","paper_title":"Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing","code":"https://github.com/cuiaiyu/dressing-in-order","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"XingGAN","metrics":{"IS":"3.476","PCKh":"0.95","SSIM":"0.778"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/xinggan-for-person-image-generation","paper_url":"https://arxiv.org/abs/2007.09278v1","paper_title":"XingGAN for Person Image Generation","code":"https://github.com/Ha0Tang/XingGAN","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"BiGraphGAN","metrics":{"IS":"3.430","PCKh":"0.97","SSIM":"0.778"},"uses_additional_data":false,"paper_date":"2020-08-10","paper":"/paper/bipartite-graph-reasoning-gans-for-person","paper_url":"https://arxiv.org/abs/2008.04381v2","paper_title":"Bipartite Graph Reasoning GANs for Person Image Generation","code":"https://github.com/Ha0Tang/BiGraphGAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"RATE","metrics":{"FID":"14.611","IS":"3.125","LPIPS":"0.218","Retrieval Top10 Recall":"30.89","SSIM":"0.774"},"uses_additional_data":false,"paper_date":"2020-05-26","paper":"/paper/region-adaptive-texture-enhancement-for","paper_url":"https://arxiv.org/abs/2005.12486v1","paper_title":"Region-adaptive Texture Enhancement for Detailed Person Image Synthesis","code":"https://github.com/Lotayou/RATE","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Progressive Pose Attention","metrics":{"DS":"0.976","IS":"3.209","PCKh":"0.96","Retrieval Top10 Recall":"17.84","SSIM":"0.773"},"uses_additional_data":false,"paper_date":"2019-04-06","paper":"/paper/progressive-pose-attention-transfer-for","paper_url":"https://arxiv.org/abs/1904.03349v3","paper_title":"Progressive Pose Attention Transfer for Person Image Generation","code":"https://github.com/tengteng95/Pose-Transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"ADGAN","metrics":{"IS":"3.364","SSIM":"0.772"},"uses_additional_data":false,"paper_date":"2020-03-27","paper":"/paper/controllable-person-image-synthesis-with","paper_url":"https://arxiv.org/abs/2003.12267v4","paper_title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","code":"https://github.com/menyifang/adgan","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"bFT","metrics":{"FID":"12.266","IS":"3.22","SSIM":"0.767"},"uses_additional_data":false,"paper_date":"2019-10-24","paper":"/paper/guided-image-to-image-translation-with-bi-1","paper_url":"https://arxiv.org/abs/1910.11328v1","paper_title":"Guided Image-to-Image Translation with Bi-Directional Feature Transformation","code":"https://github.com/vt-vl-lab/Guided-pix2pix","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"PG Squared","metrics":{"IS":"3.090","SSIM":"0.762"},"uses_additional_data":false,"paper_date":"2017-05-25","paper":"/paper/pose-guided-person-image-generation","paper_url":"http://arxiv.org/abs/1705.09368v6","paper_title":"Pose Guided Person Image Generation","code":"https://github.com/sgoldyaev/DeepFashion.ADGAN","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"Deformable GAN","metrics":{"IS":"3.439","LPIPS":"0.233","Retrieval Top10 Recall":"30.07","SSIM":"0.756"},"uses_additional_data":false,"paper_date":"2017-12-29","paper":"/paper/deformable-gans-for-pose-based-human-image","paper_url":"http://arxiv.org/abs/1801.00055v2","paper_title":"Deformable GANs for Pose-based Human Image Generation","code":"https://github.com/AliaksandrSiarohin/pose-gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Disentangled PG","metrics":{"IS":"3.228","SSIM":"0.614"},"uses_additional_data":false,"paper_date":"2017-12-07","paper":"/paper/disentangled-person-image-generation","paper_url":"http://arxiv.org/abs/1712.02621v4","paper_title":"Disentangled Person Image Generation","code":"https://github.com/charliememory/Disentangled-Person-Image-Generation","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"Leffa","metrics":{"FID":"4.23"},"uses_additional_data":false,"paper_date":"2024-12-11","paper":"/paper/learning-flow-fields-in-attention-for","paper_url":"https://arxiv.org/abs/2412.08486v2","paper_title":"Learning Flow Fields in Attention for Controllable Person Image Generation","code":"https://github.com/franciszzj/leffa","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"UPGPT","metrics":{"FID":"9.427"},"uses_additional_data":false,"paper_date":"2023-04-18","paper":"/paper/upgpt-universal-diffusion-model-for-person","paper_url":"https://arxiv.org/abs/2304.08870v2","paper_title":"UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer","code":"https://github.com/soon-yau/upgpt","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":15,"n_samples":16,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1,"n_unverified":15,"n_samples":16,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}