Unsupervised Face Alignment by Robust Nonrigid Mapping

Jianke Zhu, Luc Van Gool, Steven C. H. Hoi

ICCV 2009 pp. 1265-1272

doi:10.1109/ICCV.2009.5459325 /iccv/2009/zhu2009iccv-unsupervised/

Abstract

We propose a novel approach to unsupervised facial image alignment. Differently from previous approaches, that are confined to affine transformations on either the entire face or separate patches, we extract a nonrigid mapping between facial images. Based on a regularized face model, we frame unsupervised face alignment into the Lucas-Kanade image registration approach. We propose a robust optimization scheme to handle appearance variations. The method is fully automatic and can cope with pose variations and expressions, all in an unsupervised manner. Experiments on a large set of images showed that the approach is effective.

PDF ICCV Semantic Scholar

Cite

Text

Zhu et al. "Unsupervised Face Alignment by Robust Nonrigid Mapping." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459325

Markdown

[Zhu et al. "Unsupervised Face Alignment by Robust Nonrigid Mapping." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/zhu2009iccv-unsupervised/) doi:10.1109/ICCV.2009.5459325

BibTeX

@inproceedings{zhu2009iccv-unsupervised,
  title     = {{Unsupervised Face Alignment by Robust Nonrigid Mapping}},
  author    = {Zhu, Jianke and Van Gool, Luc and Hoi, Steven C. H.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2009},
  pages     = {1265-1272},
  doi       = {10.1109/ICCV.2009.5459325},
  url       = {https://mlanthology.org/iccv/2009/zhu2009iccv-unsupervised/}
}