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

Shengtao Xiao, Jianshu Li, Yunpeng Chen, Zhecan Wang, Jiashi Feng, Shuicheng Yan, Ashraf Kassim; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 114-122


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.

Related Material

author = {Xiao, Shengtao and Li, Jianshu and Chen, Yunpeng and Wang, Zhecan and Feng, Jiashi and Yan, Shuicheng and Kassim, Ashraf},
title = {3D-Assisted Coarse-To-Fine Extreme-Pose Facial Landmark Detection},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}