{"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/densebody-directly-regressing-dense-3d-human","title":"DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image","arxiv_id":"1903.10153","date":"2019-03-25","proceeding":null,"authors":["Pengfei Yao","Zheng Fang","Fan Wu","Yao Feng","Jiwei Li"],"abstract":"Recovering 3D human body shape and pose from 2D images is a challenging task\ndue to high complexity and flexibility of human body, and relatively less 3D\nlabeled data. Previous methods addressing these issues typically rely on\npredicting intermediate results such as body part segmentation, 2D/3D joints,\nsilhouette mask to decompose the problem into multiple sub-tasks in order to\nutilize more 2D labels. Most previous works incorporated parametric body shape\nmodel in their methods and predict parameters in low-dimensional space to\nrepresent human body. In this paper, we propose to directly regress the 3D\nhuman mesh from a single color image using Convolutional Neural Network(CNN).\nWe use an efficient representation of 3D human shape and pose which can be\npredicted through an encoder-decoder neural network. The proposed method\nachieves state-of-the-art performance on several 3D human body datasets\nincluding Human3.6M, SURREAL and UP-3D with even faster running speed.","url_abs":"http://arxiv.org/abs/1903.10153v3","url_pdf":"http://arxiv.org/pdf/1903.10153v3.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":"densebody-directly-regressing-dense-3d-human","repo_url":"https://github.com/Lotayou/densebody_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"densebody-directly-regressing-dense-3d-human","repo_url":"https://github.com/yongyct/densebody-poc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.10153","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}