ML Anthology

3D-Assisted Coarse-to-Fine Extreme-Pose Facial Landmark Detection

Shengtao Xiao, Jianshu Li, Yunpeng Chen, Zhecan Wang, Jiashi Feng, Shuicheng Yan, Ashraf A. Kassim
CVPRW 2017 pp. 2060-2068
doi:10.1109/CVPRW.2017.257 /cvprw/2017/xiao2017cvprw-3dassisted/

Abstract

We propose a novel 3D-assisted coarse-to-fine extreme-pose facial landmark detection system in this work. For a given face image, our system first refines the face bounding box with landmark locations inferred from a 3D face model generated by a Recurrent 3D Regressor at coarse level. Another R3R is then employed to fit a 3D face model onto the 2D face image cropped with the refined bounding box at fine-scale. 2D landmark locations inferred from the fitted 3D face are further adjusted with the popular 2D regression method, i.e. LBF. The 3D-assisted coarse-to-fine strategy and the 2D adjustment process explicitly ensure both the robustness to extreme face poses and bounding box disturbance and the accuracy towards pixel-level landmark displacement. Extensive experiments on the Menpo Challenge test sets demonstrate the superior performance of our system.

CVPRW Semantic Scholar

Cite

Text

Xiao et al. "3D-Assisted Coarse-to-Fine Extreme-Pose Facial Landmark Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.257

Markdown

[Xiao et al. "3D-Assisted Coarse-to-Fine Extreme-Pose Facial Landmark Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/xiao2017cvprw-3dassisted/) doi:10.1109/CVPRW.2017.257

BibTeX

@inproceedings{xiao2017cvprw-3dassisted,
  title     = {{3D-Assisted Coarse-to-Fine Extreme-Pose Facial Landmark Detection}},
  author    = {Xiao, Shengtao and Li, Jianshu and Chen, Yunpeng and Wang, Zhecan and Feng, Jiashi and Yan, Shuicheng and Kassim, Ashraf A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {2060-2068},
  doi       = {10.1109/CVPRW.2017.257},
  url       = {https://mlanthology.org/cvprw/2017/xiao2017cvprw-3dassisted/}
}