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.
@article{arxiv.1812.07603,
title = {FML: Face Model Learning from Videos},
author = {Ayush Tewari and Florian Bernard and Pablo Garrido and Gaurav Bharaj and Mohamed Elgharib and Hans-Peter Seidel and Patrick Pérez and Michael Zollhöfer and Christian Theobalt},
journal= {arXiv preprint arXiv:1812.07603},
year = {2019}
}