Recently, face alignment plays a significant role in lots of computer vision tasks. Due to the various head poses, diverse expressions and partial occlusions, face alignment has still been a great challenge. In this paper, we propose a new Deep Shape Constrained Network (DSCN) for robust face alignment. Specifically, our DSCN consists of a Shape Initialization Network (SIN) and a series of Shape Refinement Networks (SRN) in a cascaded way. SIN takes the holistic facial image as the input and generates promising preliminary facial landmarks for SRN. Each SRN consists of two task-specific streams: shape stream aiming to learn the constraint of global face shape, and the texture stream used to extract robust face feature. Finally, the network automatically learns to combine these two streams in an early fusion approach. Experimental results show that the proposed method outperforms state-of-the-art approaches on 300-W dataset, which consists of LFPW, HELEN and AFW.

最近，面部对齐在许多计算机视觉任务中起着重要作用。由于各种头部姿势，各种表情和部分遮挡，面部对齐仍然是一个巨大的挑战。在本文中，我们提出了一种新的深度约束网络（DSCN），用于鲁棒的面部对齐。具体来说，我们的DSCN由形状初始化网络（SIN）和一系列形状优化网络（SRN）以级联方式组成。SIN将整体面部图像作为输入，并为SRN生成有希望的初步面部标志。每个SRN包含两个特定于任务的流：用于学习全局脸部形状约束的形状流，以及用于提取鲁棒脸部特征的纹理流。最后，网络会自动学习以早期融合方法将这两个流合并。