{"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/mosar-monocular-semi-supervised-model-for","title":"MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading","arxiv_id":"2312.13091","date":"2023-12-20","proceeding":"CVPR 2024 1","authors":["Abdallah Dib","Luiz Gustavo Hafemann","Emeline Got","Trevor Anderson","Amin Fadaeinejad","Rafael M. O. Cruz","Marc-Andre Carbonneau"],"abstract":"Reconstructing an avatar from a portrait image has many applications in multimedia, but remains a challenging research problem. Extracting reflectance maps and geometry from one image is ill-posed: recovering geometry is a one-to-many mapping problem and reflectance and light are difficult to disentangle. Accurate geometry and reflectance can be captured under the controlled conditions of a light stage, but it is costly to acquire large datasets in this fashion. Moreover, training solely with this type of data leads to poor generalization with in-the-wild images. This motivates the introduction of MoSAR, a method for 3D avatar generation from monocular images. We propose a semi-supervised training scheme that improves generalization by learning from both light stage and in-the-wild datasets. This is achieved using a novel differentiable shading formulation. We show that our approach effectively disentangles the intrinsic face parameters, producing relightable avatars. As a result, MoSAR estimates a richer set of skin reflectance maps, and generates more realistic avatars than existing state-of-the-art methods. We also introduce a new dataset, named FFHQ-UV-Intrinsics, the first public dataset providing intrinsic face attributes at scale (diffuse, specular, ambient occlusion and translucency maps) for a total of 10k subjects. The project website and the dataset are available on the following link: https://ubisoft-laforge.github.io/character/mosar/","url_abs":"https://arxiv.org/abs/2312.13091v2","url_pdf":"https://arxiv.org/pdf/2312.13091v2.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":[],"tasks":[{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-face-reconstruction-on-realy","task":"3D Face Reconstruction","dataset":"REALY","model":"MoSAR","rank_in_archive_order":5,"of":24,"metrics":{"@cheek":"1.128 (±0.303)","@forehead":"1.950 (±0.559)","@mouth":"1.424 (±0.462)","@nose":"1.499 (±0.366)","all":"1.500"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.13091","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}