{"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/learning-person-specific-animatable-face","title":"Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model","arxiv_id":null,"date":"2025-01-01","proceeding":"CVPR 2025 1","authors":["Yuxiang Mao","Zhenfeng Fan","Zhijie Zhang","Zhiheng Zhang","Shihong Xia"],"abstract":"    Training a generic 3D face reconstruction model in a self-supervised manner using large-scale, in-the-wild 2D face image datasets enhances robustness to varying lighting conditions and occlusions while allowing the model to capture animatable wrinkle details across diverse facial expressions. However, a generic model often fails to adequately represent the unique characteristics of specific individuals. In this paper, we propose a method to train a generic base model and then transfer it to yield person-specific models by integrating lightweight adapters within the large-parameter ViT-MAE base model. These person-specific models excel at capturing individual facial shapes and detailed features while preserving the robustness and prior knowledge of detail variations from the base model. During training, we introduce a silhouette vertex re-projection loss to address boundary \"landmark marching\" issues on the 3D face caused by pose variations. Additionally, we employ an innovative teacher-student loss to leverage the inherent strengths of UNet in feature boundary localization for training our detail MAE. Quantitative and qualitative experiments demonstrate that our approach achieves state-of-the-art performance in face alignment, detail accuracy, and richness. The source code is available at https://github.com/danielmao2000/person-specific-animatable-face.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2025/html/Mao_Learning_Person-Specific_Animatable_Face_Models_from_In-the-Wild_Images_via_a_CVPR_2025_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2025/papers/Mao_Learning_Person-Specific_Animatable_Face_Models_from_In-the-Wild_Images_via_a_CVPR_2025_paper.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":"learning-person-specific-animatable-face","repo_url":"https://github.com/danielmao2000/person-specific-animatable-face","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"face-reconstruction","task_name":"Face Reconstruction"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}