Papers › MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading

MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading

20 Dec 2023CVPR 2024 1arXiv:2312.13091archive 2025-07-28

Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-Andre Carbonneau

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/

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Face Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction REALY MoSAR @cheek 1.128 (±0.303) #5 of 24 Archive leaderboard report
3D Face Reconstruction REALY MoSAR @forehead 1.950 (±0.559) #5 of 24 Archive leaderboard report
3D Face Reconstruction REALY MoSAR @mouth 1.424 (±0.462) #5 of 24 Archive leaderboard report
3D Face Reconstruction REALY MoSAR @nose 1.499 (±0.366) #5 of 24 Archive leaderboard report
3D Face Reconstruction REALY MoSAR all 1.500 #5 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections