{"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-normalized-image-generation-for-person","title":"Pose-Normalized Image Generation for Person Re-identification","arxiv_id":"1712.02225","date":"2017-12-06","proceeding":"ECCV 2018 9","authors":["Xuelin Qian","Yanwei Fu","Tao Xiang","Wenxuan Wang","Jie Qiu","Yang Wu","Yu-Gang Jiang","xiangyang xue"],"abstract":"Person Re-identification (re-id) faces two major challenges: the lack of\ncross-view paired training data and learning discriminative identity-sensitive\nand view-invariant features in the presence of large pose variations. In this\nwork, we address both problems by proposing a novel deep person image\ngeneration model for synthesizing realistic person images conditional on the\npose. The model is based on a generative adversarial network (GAN) designed\nspecifically for pose normalization in re-id, thus termed pose-normalization\nGAN (PN-GAN). With the synthesized images, we can learn a new type of deep\nre-id feature free of the influence of pose variations. We show that this\nfeature is strong on its own and complementary to features learned with the\noriginal images. Importantly, under the transfer learning setting, we show that\nour model generalizes well to any new re-id dataset without the need for\ncollecting any training data for model fine-tuning. The model thus has the\npotential to make re-id model truly scalable.","url_abs":"http://arxiv.org/abs/1712.02225v6","url_pdf":"http://arxiv.org/pdf/1712.02225v6.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-normalized-image-generation-for-person","repo_url":"https://github.com/naiq/PN_GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"pose-normalized-image-generation-for-person","repo_url":"https://github.com/NVlabs/DG-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-market-1501-1","task":"Person Re-Identification","dataset":"Market-1501->DukeMTMC-reID","model":"PN-GAN [qian2018pose]","rank_in_archive_order":2,"of":2,"metrics":{"Rank-1":"29.9","mAP":"15.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.02225","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}