其他
【CVPR2016论文快讯】面部特征点定位的最新进展
CVPR2016刚刚落下帷幕,本文对面部特征点定位的论文做一个简单总结,让大家快速了解该领域最新的研究进展,希望能给读者们带来启发。CVPR2016相关的文章大致可以分为三大类:处理大姿态问题,处理表情问题,处理遮挡问题。
1.1 Face Alignment Across Large Poses: A 3D Solution [1]
3D人脸形状模型可以表示为平均3D人脸形状A0与若干表征身份、表情的基向量Aid和Aexp通过p参数组合而成。面部特征点定位问题(预测U)可以转变为同时预测投影矩阵m和3D人脸形状模型参数p。算法的整体框架图如下所示:
[2] Amin Jourabloo, Xiaoming Liu. Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting. CVPR 2016.
[3] Shizhan Zhu, Cheng Li, Chen-Change Loy, Xiaoou Tang. Unconstrained Face Alignment via Cascaded Compositional Learning. CVPR 2016.
[4] Xuehan Xiong, De la Torre Fernando. Global supervised descent method. CVPR 2015.
[5] Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun. Face Alignment at 3000 FPS via Regressing Local Binary Features. CVPR 2014.
[6] Yue Wu, Qiang Ji. Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection. CVPR 2016.
[7] Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen. Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders. CVPR 2016.
[8] George Trigeorgis, Patrick Snape, Mihalis A. Nicolaou, Epameinondas Antonakos, Stefanos Zafeiriou. Mnemonic Descent Method: A Recurrent Process Applied for End-To-End Face Alignment. CVPR 2016.