{"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/rafare-learning-robust-and-accurate-non","title":"RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs","arxiv_id":"2302.05486","date":"2023-02-10","proceeding":null,"authors":["Longwei Guo","Hao Zhu","Yuanxun Lu","Menghua Wu","Xun Cao"],"abstract":"We propose a robust and accurate non-parametric method for single-view 3D face reconstruction (SVFR). While tremendous efforts have been devoted to parametric SVFR, a visible gap still lies between the result 3D shape and the ground truth. We believe there are two major obstacles: 1) the representation of the parametric model is limited to a certain face database; 2) 2D images and 3D shapes in the fitted datasets are distinctly misaligned. To resolve these issues, a large-scale pseudo 2D\\&3D dataset is created by first rendering the detailed 3D faces, then swapping the face in the wild images with the rendered face. These pseudo 2D&3D pairs are created from publicly available datasets which eliminate the gaps between 2D and 3D data while covering diverse appearances, poses, scenes, and illumination. We further propose a non-parametric scheme to learn a well-generalized SVFR model from the created dataset, and the proposed hierarchical signed distance function turns out to be effective in predicting middle-scale and small-scale 3D facial geometry. Our model outperforms previous methods on FaceScape-wild/lab and MICC benchmarks and is well generalized to various appearances, poses, expressions, and in-the-wild environments. The code is released at http://github.com/zhuhao-nju/rafare .","url_abs":"https://arxiv.org/abs/2302.05486v1","url_pdf":"https://arxiv.org/pdf/2302.05486v1.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":"rafare-learning-robust-and-accurate-non","repo_url":"https://github.com/zhuhao-nju/rafare","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":"face-reconstruction","task_name":"Face Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.05486","atlas_url":"https://app.syntology.ai/?focus=2302.05486","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}