Deep shape constrained network for robust face alignment

摘要

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. (C) 2020 Elsevier B.V. All rights reserved.