{"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/sherf-generalizable-human-nerf-from-a-single","title":"SHERF: Generalizable Human NeRF from a Single Image","arxiv_id":"2303.12791","date":"2023-03-22","proceeding":"ICCV 2023 1","authors":["Shoukang Hu","Fangzhou Hong","Liang Pan","Haiyi Mei","Lei Yang","Ziwei Liu"],"abstract":"Existing Human NeRF methods for reconstructing 3D humans typically rely on multiple 2D images from multi-view cameras or monocular videos captured from fixed camera views. However, in real-world scenarios, human images are often captured from random camera angles, presenting challenges for high-quality 3D human reconstruction. In this paper, we propose SHERF, the first generalizable Human NeRF model for recovering animatable 3D humans from a single input image. SHERF extracts and encodes 3D human representations in canonical space, enabling rendering and animation from free views and poses. To achieve high-fidelity novel view and pose synthesis, the encoded 3D human representations should capture both global appearance and local fine-grained textures. To this end, we propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding. Global features enhance the information extracted from the single input image and complement the information missing from the partial 2D observation. Point-level features provide strong clues of 3D human structure, while pixel-aligned features preserve more fine-grained details. To effectively integrate the 3D-aware hierarchical feature bank, we design a feature fusion transformer. Extensive experiments on THuman, RenderPeople, ZJU_MoCap, and HuMMan datasets demonstrate that SHERF achieves state-of-the-art performance, with better generalizability for novel view and pose synthesis.","url_abs":"https://arxiv.org/abs/2303.12791v2","url_pdf":"https://arxiv.org/pdf/2303.12791v2.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":"sherf-generalizable-human-nerf-from-a-single","repo_url":"https://github.com/skhu101/sherf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-human-reconstruction","task_name":"3D Human Reconstruction"},{"task_slug":"nerf","task_name":"NeRF"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.12791","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}