{"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/high-fidelity-3d-human-digitization-from","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","arxiv_id":"2303.15108","date":"2023-03-27","proceeding":"CVPR 2023 1","authors":["Sang-Hun Han","Min-Gyu Park","Ju Hong Yoon","Ju-Mi Kang","Young-Jae Park","Hae-Gon Jeon"],"abstract":"High-quality 3D human body reconstruction requires high-fidelity and large-scale training data and appropriate network design that effectively exploits the high-resolution input images. To tackle these problems, we propose a simple yet effective 3D human digitization method called 2K2K, which constructs a large-scale 2K human dataset and infers 3D human models from 2K resolution images. The proposed method separately recovers the global shape of a human and its details. The low-resolution depth network predicts the global structure from a low-resolution image, and the part-wise image-to-normal network predicts the details of the 3D human body structure. The high-resolution depth network merges the global 3D shape and the detailed structures to infer the high-resolution front and back side depth maps. Finally, an off-the-shelf mesh generator reconstructs the full 3D human model, which are available at https://github.com/SangHunHan92/2K2K. In addition, we also provide 2,050 3D human models, including texture maps, 3D joints, and SMPL parameters for research purposes. In experiments, we demonstrate competitive performance over the recent works on various datasets.","url_abs":"https://arxiv.org/abs/2303.15108v1","url_pdf":"https://arxiv.org/pdf/2303.15108v1.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":"high-fidelity-3d-human-digitization-from","repo_url":"https://github.com/sanghunhan92/2k2k","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"2k","task_name":"2k"},{"task_slug":"3d-human-reconstruction","task_name":"3D Human Reconstruction"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"high-resolution-input","method_name":"High-resolution input"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-reconstruction-on-customhumans","task":"3D Human Reconstruction","dataset":"CustomHumans","model":"2K2K","rank_in_archive_order":8,"of":8,"metrics":{"Chamfer Distance P-to-S":"2.488","Chamfer Distance S-to-P":"3.292","Normal Consistency":"0.796","f-Score":"30.186"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.15108","atlas_url":"https://app.syntology.ai/?focus=2303.15108","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}