{"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/pose-guided-person-image-generation","title":"Pose Guided Person Image Generation","arxiv_id":"1705.09368","date":"2017-05-25","proceeding":"NeurIPS 2017 12","authors":["Liqian Ma","Xu Jia","Qianru Sun","Bernt Schiele","Tinne Tuytelaars","Luc van Gool"],"abstract":"This paper proposes the novel Pose Guided Person Generation Network (PG$^2$)\nthat allows to synthesize person images in arbitrary poses, based on an image\nof that person and a novel pose. Our generation framework PG$^2$ utilizes the\npose information explicitly and consists of two key stages: pose integration\nand image refinement. In the first stage the condition image and the target\npose are fed into a U-Net-like network to generate an initial but coarse image\nof the person with the target pose. The second stage then refines the initial\nand blurry result by training a U-Net-like generator in an adversarial way.\nExtensive experimental results on both 128$\\times$64 re-identification images\nand 256$\\times$256 fashion photos show that our model generates high-quality\nperson images with convincing details.","url_abs":"http://arxiv.org/abs/1705.09368v6","url_pdf":"http://arxiv.org/pdf/1705.09368v6.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":"pose-guided-person-image-generation","repo_url":"https://github.com/chuanqichen/deepcoaching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pose-guided-person-image-generation","repo_url":"https://github.com/sgoldyaev/DeepFashion.ADGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"gesture-to-gesture-translation","task_name":"Gesture-to-Gesture Translation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"pose-transfer","task_name":"Pose Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gesture-to-gesture-translation-on-ntu-hand","task":"Gesture-to-Gesture Translation","dataset":"NTU Hand Digit","model":"PG2","rank_in_archive_order":4,"of":6,"metrics":{"AMT":"3.5","IS":"2.4152","PSNR":"28.2403"},"uses_additional_data":false},{"leaderboard":"/sota/gesture-to-gesture-translation-on-senz3d","task":"Gesture-to-Gesture Translation","dataset":"Senz3D","model":"PG2","rank_in_archive_order":3,"of":6,"metrics":{"AMT":"2.8","IS":"3.3699","PSNR":"26.5138"},"uses_additional_data":false},{"leaderboard":"/sota/pose-transfer-on-deep-fashion","task":"Pose Transfer","dataset":"Deep-Fashion","model":"PG Squared","rank_in_archive_order":8,"of":12,"metrics":{"IS":"3.090","SSIM":"0.762"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.09368","atlas_url":"https://app.syntology.ai/?focus=1705.09368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}