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

no code implementations • 20 Dec 2023 • Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-Andre Carbonneau

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.

3D Face Reconstruction

A Scale-Invariant Trajectory Simplification Method for Efficient Data Collection in Videos

1 code implementation • 3 Apr 2023 • Yang Liu, Luiz Gustavo Hafemann

In a semi-automated data collection pipeline, this can be achieved by running a baseline detection and tracking algorithm, and relying on manual correction to add/remove/change bounding boxes on each frame, as well as resolving errors in the associations over frames (track switches).