{"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/3dpeople-modeling-the-geometry-of-dressed","title":"3DPeople: Modeling the Geometry of Dressed Humans","arxiv_id":"1904.04571","date":"2019-04-09","proceeding":"ICCV 2019 10","authors":["Albert Pumarola","Jordi Sanchez","Gary P. T. Choi","Alberto Sanfeliu","Francesc Moreno-Noguer"],"abstract":"Recent advances in 3D human shape estimation build upon parametric\nrepresentations that model very well the shape of the naked body, but are not\nappropriate to represent the clothing geometry. In this paper, we present an\napproach to model dressed humans and predict their geometry from single images.\nWe contribute in three fundamental aspects of the problem, namely, a new\ndataset, a novel shape parameterization algorithm and an end-to-end deep\ngenerative network for predicting shape.\n  First, we present 3DPeople, a large-scale synthetic dataset with 2.5 Million\nphoto-realistic images of 80 subjects performing 70 activities and wearing\ndiverse outfits. Besides providing textured 3D meshes for clothes and body, we\nannotate the dataset with segmentation masks, skeletons, depth, normal maps and\noptical flow. All this together makes 3DPeople suitable for a plethora of\ntasks.\n  We then represent the 3D shapes using 2D geometry images. To build these\nimages we propose a novel spherical area-preserving parameterization algorithm\nbased on the optimal mass transportation method. We show this approach to\nimprove existing spherical maps which tend to shrink the elongated parts of the\nfull body models such as the arms and legs, making the geometry images\nincomplete.\n  Finally, we design a multi-resolution deep generative network that, given an\ninput image of a dressed human, predicts his/her geometry image (and thus the\nclothed body shape) in an end-to-end manner. We obtain very promising results\nin jointly capturing body pose and clothing shape, both for synthetic\nvalidation and on the wild images.","url_abs":"http://arxiv.org/abs/1904.04571v1","url_pdf":"http://arxiv.org/pdf/1904.04571v1.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":[],"tasks":[{"task_slug":"3d-human-shape-estimation","task_name":"3D Human Shape Estimation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[{"slug":"3dpeople-dataset","name":"3DPeople Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.04571","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}