Pix2Face: Direct 3D Face Model Estimation
Abstract
An efficient, fully automatic method for 3D face shape and pose estimation in unconstrained 2D imagery is presented. The proposed method jointly estimates a dense set of 3D landmarks and facial geometry using a single pass of a modified version of the popular "U-Net" neural network architecture. Additionally, we propose a method for directly estimating a set of 3D Morphable Model (3DMM) parameters, using the estimated 3D landmarks and geometry as constraints in a simple linear system. Qualitative modeling results are presented, as well as quantitative evaluation of predicted 3D face landmarks in unconstrained video sequences.
Cite
Text
Crispell and Bazik. "Pix2Face: Direct 3D Face Model Estimation." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.295Markdown
[Crispell and Bazik. "Pix2Face: Direct 3D Face Model Estimation." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/crispell2017iccvw-pix2face/) doi:10.1109/ICCVW.2017.295BibTeX
@inproceedings{crispell2017iccvw-pix2face,
title = {{Pix2Face: Direct 3D Face Model Estimation}},
author = {Crispell, Daniel E. and Bazik, Maxim},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2017},
pages = {2512-2518},
doi = {10.1109/ICCVW.2017.295},
url = {https://mlanthology.org/iccvw/2017/crispell2017iccvw-pix2face/}
}