English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

FML: Face Model Learning from Videos

MPS-Authors
/persons/resource/persons206546

Tewari,  Ayush
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons214986

Bernard,  Florian
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons229949

Elgharib,  Mohamed
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45449

Seidel,  Hans-Peter
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons136490

Zollhöfer,  Michael
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

Theobalt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;

Locator
Fulltext (public)

arXiv:1812.07603.pdf
(Preprint), 8MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Tewari, A., Bernard, F., Garrido, P., Bharaj, G., Elgharib, M., Seidel, H.-P., et al. (2018). FML: Face Model Learning from Videos. Retrieved from http://arxiv.org/abs/1812.07603.


Cite as: http://hdl.handle.net/21.11116/0000-0002-EF79-A
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.