Adaptive 3D Face Reconstruction from Unconstrained Photo Collections
Abstract
Given a collection of "in-the-wild" face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information. Motivated by the success of recent face reconstruction techniques on large photo collections, we extend prior work to adapt to low quality photo collections with fewer images. We achieve this by fitting a 3D Morphable Model to form a personalized template and developing a novel photometric stereo formulation, under a coarse-to-fine scheme. Superior experimental results are reported on synthetic and real-world photo collections.
Cite
Text
Roth et al. "Adaptive 3D Face Reconstruction from Unconstrained Photo Collections." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.455Markdown
[Roth et al. "Adaptive 3D Face Reconstruction from Unconstrained Photo Collections." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/roth2016cvpr-adaptive/) doi:10.1109/CVPR.2016.455BibTeX
@inproceedings{roth2016cvpr-adaptive,
title = {{Adaptive 3D Face Reconstruction from Unconstrained Photo Collections}},
author = {Roth, Joseph and Tong, Yiying and Liu, Xiaoming},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2016},
doi = {10.1109/CVPR.2016.455},
url = {https://mlanthology.org/cvpr/2016/roth2016cvpr-adaptive/}
}