KMS Chongqing Institute of Green and Intelligent Technology, CAS
Unconstrained Face Alignment Without Face Detection | |
Shao, Xiaohu1,2; Xing, Junliang3; Lv, Jiangjing1,2; Xiao, Chunlin4; Liu, Pengcheng1; Feng, Youji1; Cheng, Cheng1 | |
2017 | |
摘要 | This paper introduces our submission to the 2nd Facial Landmark Localisation Competition. We present a deep architecture to directly detect facial landmarks without using face detection as an initialization. The architecture consists of two stages, a Basic Landmark Prediction Stage and a Whole Landmark Regression Stage. At the former stage, given an input image, the basic landmarks of all faces are detected by a sub-network of landmark heatmap and affinity field prediction. At the latter stage, the coarse canonical face and the pose can be generated by a Pose Splitting Layer based on the visible basic landmarks. According to its pose, each canonical state is distributed to the corresponding branch of the shape regression sub-networks for the whole landmark detection. Experimental results show that our method obtains promising results on the 300-W dataset, and achieves superior performances over the baselines of the semi-frontal and the profile categories in this competition. © 2017 IEEE. |
语种 | 英语 |
DOI | 10.1109/CVPRW.2017.258 |
会议(录)名称 | 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 |
页码 | 2069-2077 |
收录类别 | EI |
会议地点 | Honolulu, HI, United states |
会议日期 | July 21, 2017 - July 26, 2017 |