Dense Face Alignment
2017 IEEE International Conference on Computer Vision Workshops (ICCVW)(2017)
摘要
Face alignment is a classic problem in the computer vision field. Previous works mostly focus on sparse alignment with a limited number of facial landmark points, i.e., facial landmark detection. In this paper, for the first time, we aim at providing a very dense 3D alignment for large-pose face images. To achieve this, we train a CNN to estimate the 3D face shape, which not only aligns limited facial landmarks but also fits face contours and SIFT feature points. Moreover, we also address the bottleneck of training CNN with multiple datasets, due to different landmark markups on different datasets, such as 5, 34, 68. Experimental results show our method not only provides high-quality, dense 3D face fitting but also outperforms the state-of-the-art facial landmark detection methods on the challenging datasets. Our model can run at real time during testing.
更多查看译文
关键词
dense face alignment,computer vision field,sparse alignment,facial landmark points,dense 3D alignment,face images,3D face shape,facial landmarks,face contours,training CNN,multiple datasets,dense 3D face fitting,facial landmark detection methods,challenging datasets,landmark markups,SIFT feature points
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络