Dual-Attention GAN for Large-Pose Face Frontalization

by   Yu Yin, et al.

Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches, this problem is still challenging due to significant pose and illumination discrepancy. In this paper, we present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization by capturing both contextual dependencies and local consistency during GAN training. Specifically, a self-attention-based generator is introduced to integrate local features with their long-range dependencies yielding better feature representations, and hence generate faces that preserve identities better, especially for larger pose angles. Moreover, a novel face-attention-based discriminator is applied to emphasize local features of face regions, and hence reinforce the realism of synthetic frontal faces. Guided by semantic segmentation, four independent discriminators are used to distinguish between different aspects of a face ( skin, keypoints, hairline, and frontalized face). By introducing these two complementary attention mechanisms in generator and discriminator separately, we can learn a richer feature representation and generate identity preserving inference of frontal views with much finer details (i.e., more accurate facial appearance and textures) comparing to the state-of-the-art. Quantitative and qualitative experimental results demonstrate the effectiveness and efficiency of our DA-GAN approach.



There are no comments yet.


page 1

page 3

page 4

page 5

page 6

page 7


Representation Learning by Rotating Your Faces

The large pose discrepancy between two face images is one of the fundame...

Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision

Despite recent advances in deep learning-based face frontalization metho...

Heterogeneous Face Frontalization via Domain Agnostic Learning

Recent advances in deep convolutional neural networks (DCNNs) have shown...

BoostGAN for Occlusive Profile Face Frontalization and Recognition

There are many facts affecting human face recognition, such as pose, occ...

SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination

Despite generative adversarial networks (GANs) can hallucinate photo-rea...

FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

We present Face Swapping GAN (FSGAN) for face swapping and reenactment. ...

A study on the use of Boundary Equilibrium GAN for Approximate Frontalization of Unconstrained Faces to aid in Surveillance

Face frontalization is the process of synthesizing frontal facing views ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.