{"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/a-generative-model-of-people-in-clothing","title":"A Generative Model of People in Clothing","arxiv_id":"1705.04098","date":"2017-05-11","proceeding":"ICCV 2017 10","authors":["Christoph Lassner","Gerard Pons-Moll","Peter V. Gehler"],"abstract":"We present the first image-based generative model of people in clothing for\nthe full body. We sidestep the commonly used complex graphics rendering\npipeline and the need for high-quality 3D scans of dressed people. Instead, we\nlearn generative models from a large image database. The main challenge is to\ncope with the high variance in human pose, shape and appearance. For this\nreason, pure image-based approaches have not been considered so far. We show\nthat this challenge can be overcome by splitting the generating process in two\nparts. First, we learn to generate a semantic segmentation of the body and\nclothing. Second, we learn a conditional model on the resulting segments that\ncreates realistic images. The full model is differentiable and can be\nconditioned on pose, shape or color. The result are samples of people in\ndifferent clothing items and styles. The proposed model can generate entirely\nnew people with realistic clothing. In several experiments we present\nencouraging results that suggest an entirely data-driven approach to people\ngeneration is possible.","url_abs":"http://arxiv.org/abs/1705.04098v3","url_pdf":"http://arxiv.org/pdf/1705.04098v3.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":"a-generative-model-of-people-in-clothing","repo_url":"https://github.com/classner/generating_people","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.04098","atlas_url":"https://app.syntology.ai/?focus=1705.04098","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}