{"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/detailed-human-avatars-from-monocular-video","title":"Detailed Human Avatars from Monocular Video","arxiv_id":"1808.01338","date":"2018-08-03","proceeding":null,"authors":["Thiemo Alldieck","Marcus Magnor","Weipeng Xu","Christian Theobalt","Gerard Pons-Moll"],"abstract":"We present a novel method for high detail-preserving human avatar creation\nfrom monocular video. A parameterized body model is refined and optimized to\nmaximally resemble subjects from a video showing them from all sides. Our\navatars feature a natural face, hairstyle, clothes with garment wrinkles, and\nhigh-resolution texture. Our paper contributes facial landmark and\nshading-based human body shape refinement, a semantic texture prior, and a\nnovel texture stitching strategy, resulting in the most sophisticated-looking\nhuman avatars obtained from a single video to date. Numerous results show the\nrobustness and versatility of our method. A user study illustrates its\nsuperiority over the state-of-the-art in terms of identity preservation, level\nof detail, realism, and overall user preference.","url_abs":"http://arxiv.org/abs/1808.01338v1","url_pdf":"http://arxiv.org/pdf/1808.01338v1.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":"detailed-human-avatars-from-monocular-video","repo_url":"https://github.com/thmoa/semantic_human_texture_stitching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.01338","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}