Abstract

Face alignment, which fifits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45◦ ), lacking the ability to align faces in large poses up to 90◦ . The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profifile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profifile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fifitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profifile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves signifificant improvements over state-of-the-art methods.