Fast and Precise Face Alignment and 3D Shape Reconstruction from a Single 2D Image
Abstract
Many face recognition applications require a precise 3D reconstruction of the shape of the face, even when only a single 2D image is available. We present a novel regression approach that learns to detect facial landmark points and estimate their 3D shape rapidly and accurately from a single face image. The main idea is to regress a function f (.) that maps 2D images of faces to their corresponding 3D shape from a large number of sample face images under varying pose, illumination, identity and expression. To model the non-linearity of this function, we use a deep neural network and demonstrate how it can be efficiently trained using a large number of samples. During testing, our algorithm runs at more than 30 frames/s on an i7 desktop. This algorithm was the top 2 performer in the 3DFAW Challenge.
Cite
Text
Zhao et al. "Fast and Precise Face Alignment and 3D Shape Reconstruction from a Single 2D Image." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-48881-3_41Markdown
[Zhao et al. "Fast and Precise Face Alignment and 3D Shape Reconstruction from a Single 2D Image." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/zhao2016eccv-fast/) doi:10.1007/978-3-319-48881-3_41BibTeX
@inproceedings{zhao2016eccv-fast,
title = {{Fast and Precise Face Alignment and 3D Shape Reconstruction from a Single 2D Image}},
author = {Zhao, Ruiqi and Wang, Yan and Benitez-Quiroz, Carlos Fabian and Liu, Yaojie and Martínez, Aleix M.},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {590-603},
doi = {10.1007/978-3-319-48881-3_41},
url = {https://mlanthology.org/eccv/2016/zhao2016eccv-fast/}
}