{"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/pcgan-partition-controlled-human-image","title":"PCGAN: Partition-Controlled Human Image Generation","arxiv_id":"1811.09928","date":"2018-11-25","proceeding":null,"authors":["Dong Liang","Rui Wang","Xiaowei Tian","Cong Zou"],"abstract":"Human image generation is a very challenging task since it is affected by\nmany factors. Many human image generation methods focus on generating human\nimages conditioned on a given pose, while the generated backgrounds are often\nblurred.In this paper,we propose a novel Partition-Controlled GAN to generate\nhuman images according to target pose and background. Firstly, human poses in\nthe given images are extracted, and foreground/background are partitioned for\nfurther use. Secondly, we extract and fuse appearance features, pose features\nand background features to generate the desired images. Experiments on\nMarket-1501 and DeepFashion datasets show that our model not only generates\nrealistic human images but also produce the human pose and background as we\nwant. Extensive experiments on COCO and LIP datasets indicate the potential of\nour method.","url_abs":"http://arxiv.org/abs/1811.09928v1","url_pdf":"http://arxiv.org/pdf/1811.09928v1.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":"pcgan-partition-controlled-human-image","repo_url":"https://github.com/AlanIIE/PCGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}