Face Alignment by coarse-to-fine shape searching

Shizhan Zhu^1,2, Cheng Li², Chen Change Loy^1,3, Xiaoou Tang^1,3

¹Department of Information Engineering, The Chinese University of Hong Kong

²SenseTime Group

³Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

Abstract

We present a novel face alignment framework based on coarse-to-fine shape searching. Unlike the conventional cascaded regression approaches that start with an initial shape and refine the shape in a cascaded manner, our approach begins with a coarse search over a shape space that contains diverse shapes, and employs the coarse solution to constrain subsequent finer search of shapes. The unique stage-by-stage progressive and adaptive search i) prevents the final solution from being trapped in local optima due to poor initialisation, a common problem encountered by cascaded regression approaches; and ii) improves the robustness in coping with large pose variations. The framework demonstrates real-time performance and state-of-theart results on various benchmarks including the challenging 300-W dataset.

Demo Video

Code Release

Our full version codes (open source, including training) is now available at the github page https://github.com/zhusz/CVPR15-CFSS. Please refer to that page for details.

A pre-trained model (for the original paper) can be downloaded from here.

A pre-trained model (trained for Matlab VJ face detection box) can be downloaded from here.

Reference

Shizhan Zhu, Cheng Li, Chen Change Loy, Xiaoou Tang. Face alignment by coarse-to-fine shape searching, in Proceedings of Computer Vision and Pattern Recognition (CVPR), 2015.