June
2018
Modeling Facial Geometry Using Compositional VAEs
Authors:
Abstract:
We propose a method for learning non-linear face geometry representations using deep generative models. Our model is a variational autoencoder with multiple levels of hidden variables where lower layers capture global geometry and higher ones encode more local deformations. Based on that, we propose a new parameterization of facial geometry that naturally decomposes the structure of the human face into a set of semantically meaningful levels of detail. This parameterization enables us to do model fitting while capturing varying level of detail under different types of geometrical constraints.
copied = false, 2000);
">
@conference{Bagautdinov-2018-122180,
author = {Timur Bagautdinov And Chenglei Wu And Jason Saragih And Pascal Fua And Yaser Sheikh},
title = {Modeling Facial Geometry Using Compositional VAEs},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2018},
month = {June},
pages = {3877 - 3886},
}
author = {Timur Bagautdinov And Chenglei Wu And Jason Saragih And Pascal Fua And Yaser Sheikh},
title = {Modeling Facial Geometry Using Compositional VAEs},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2018},
month = {June},
pages = {3877 - 3886},
}