FML: Face Model Learning From Videos

Ayush Tewari, Florian Bernard, Pablo Garrido, Gaurav Bharaj, Mohamed Elgharib, Hans-Peter Seidel, Patrick Perez, Michael Zollhofer, Christian Theobalt
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1 . We propose multi-frame self-supervised training of a deep network based on in-the-wild video data for jointly learning a face model and 3D face reconstruction. Our approach successfully disentangles facial shape, appearance, expression, and scene illumination. Abstract Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing
more » ... methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multiframe consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction.
doi:10.1109/cvpr.2019.01107 dblp:conf/cvpr/TewariB0BESPZT19 fatcat:6gf5b75bkzbldhzbyqnun4okzm