{"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/trihuman-a-real-time-and-controllable-tri","title":"TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis","arxiv_id":"2312.05161","date":"2023-12-08","proceeding":null,"authors":["Heming Zhu","Fangneng Zhan","Christian Theobalt","Marc Habermann"],"abstract":"Creating controllable, photorealistic, and geometrically detailed digital doubles of real humans solely from video data is a key challenge in Computer Graphics and Vision, especially when real-time performance is required. Recent methods attach a neural radiance field (NeRF) to an articulated structure, e.g., a body model or a skeleton, to map points into a pose canonical space while conditioning the NeRF on the skeletal pose. These approaches typically parameterize the neural field with a multi-layer perceptron (MLP) leading to a slow runtime. To address this drawback, we propose TriHuman a novel human-tailored, deformable, and efficient tri-plane representation, which achieves real-time performance, state-of-the-art pose-controllable geometry synthesis as well as photorealistic rendering quality. At the core, we non-rigidly warp global ray samples into our undeformed tri-plane texture space, which effectively addresses the problem of global points being mapped to the same tri-plane locations. We then show how such a tri-plane feature representation can be conditioned on the skeletal motion to account for dynamic appearance and geometry changes. Our results demonstrate a clear step towards higher quality in terms of geometry and appearance modeling of humans as well as runtime performance.","url_abs":"https://arxiv.org/abs/2312.05161v1","url_pdf":"https://arxiv.org/pdf/2312.05161v1.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":"trihuman-a-real-time-and-controllable-tri","repo_url":"https://github.com/kv2000/DeepCharacters_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.05161","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}