Zhu Xiangyu, Liu Xiaoming, Lei Zhen, Li Stan Z
IEEE Trans Pattern Anal Mach Intell. 2019 Jan;41(1):78-92. doi: 10.1109/TPAMI.2017.2778152. Epub 2017 Nov 28.
Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in the computer vision community. However, most algorithms are designed for faces in small to medium poses (yaw angle is smaller than 45 degree), which lack the ability to align faces in large poses up to 90 degree. The challenges are three-fold. First, the commonly used landmark face model assumes that all the landmarks are visible and is therefore not suitable for large poses. Second, the face appearance varies more drastically across large poses, from the frontal view to the profile view. Third, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks. We also utilize 3D information to synthesize face images in profile views to provide abundant samples for training. Experiments on the challenging AFLW database show that the proposed approach achieves significant improvements over the state-of-the-art methods.
人脸对齐旨在将人脸模型与图像匹配并提取面部像素的语义信息，一直是计算机视觉领域的重要研究课题。然而，大多数算法都是针对中小姿态（偏航角小于45度）的人脸设计的，缺乏对齐高达90度大姿态人脸的能力。这些挑战主要有三个方面。首先，常用的地标人脸模型假设所有地标都可见，因此不适用于大姿态。其次，从正视图到侧视图，大姿态下的人脸外观变化更为剧烈。第三，由于必须猜测不可见的地标，在大姿态下标记地标极具挑战性。在本文中，我们提出在一个名为3D密集人脸对齐（3DDFA）的新对齐框架中解决这三个挑战，其中通过级联卷积神经网络将密集3D可变形模型（3DMM）拟合到图像上。我们还利用3D信息合成侧视图中的人脸图像，为训练提供丰富的样本。在具有挑战性的AFLW数据库上的实验表明，所提出的方法比现有方法有显著改进。
