FML: Face Model Learning from Videos

CVPR 2019 (Oral)


A. Tewari 1 F. Bernard 1 P. Garrido 2 G. Bharaj 2 M. Elgharib 1 H-P. Seidel 1 P. Perez 3 M. Zollhöfer 4 C.Theobalt 1
1MPI Informatics, Saarland Informatics Campus 2Technicolor 3Valeo.ai 4Stanford University




Full Video More Qualitative Results


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 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 multi-frame 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.


Paper Supplemental

Bibtex