{"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/learning-to-reconstruct-people-in-clothing","title":"Learning to Reconstruct People in Clothing from a Single RGB Camera","arxiv_id":"1903.05885","date":"2019-03-14","proceeding":"CVPR 2019 6","authors":["Thiemo Alldieck","Marcus Magnor","Bharat Lal Bhatnagar","Christian Theobalt","Gerard Pons-Moll"],"abstract":"We present a learning-based model to infer the personalized 3D shape of\npeople from a few frames (1-8) of a monocular video in which the person is\nmoving, in less than 10 seconds with a reconstruction accuracy of 5mm. Our\nmodel learns to predict the parameters of a statistical body model and instance\ndisplacements that add clothing and hair to the shape. The model achieves fast\nand accurate predictions based on two key design choices. First, by predicting\nshape in a canonical T-pose space, the network learns to encode the images of\nthe person into pose-invariant latent codes, where the information is fused.\nSecond, based on the observation that feed-forward predictions are fast but do\nnot always align with the input images, we predict using both, bottom-up and\ntop-down streams (one per view) allowing information to flow in both\ndirections. Learning relies only on synthetic 3D data. Once learned, the model\ncan take a variable number of frames as input, and is able to reconstruct\nshapes even from a single image with an accuracy of 6mm. Results on 3 different\ndatasets demonstrate the efficacy and accuracy of our approach.","url_abs":"http://arxiv.org/abs/1903.05885v2","url_pdf":"http://arxiv.org/pdf/1903.05885v2.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":"learning-to-reconstruct-people-in-clothing","repo_url":"https://github.com/thmoa/octopus","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.05885","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}