Makeup is widely used to improve facial attractiveness and is well accepted by the public. However, different makeup styles will result in significant facial appearance changes. It remains a challenging problem
to match makeup and non-makeup face images. This paper proposes a learning from generation approach
for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN). To alleviate
the negative effects from makeup, we first generate non-makeup images from makeup ones, and then
use the synthesized non-makeup images for further verification. Specifically, there are two adversarial
sub-networks on different levels in BLAN, with the one on pixel level for reconstructing appealing facial
images and the other on feature level for preserving identity information. For the non-makeup image
generation module, a two-path network that involves both global and local structures is applied to improve the synthesis quality. Moreover, we make the generator well constrained by incorporating multiple
perceptual losses. All the modules are embedded in an end-to-end network and jointly reduce the sensing gap between makeup and non-makeup images. Experimental results on three benchmark makeup
face datasets demonstrate that our method achieves state-of-the-art verification accuracy across makeup
status and can produce photo-realistic non-makeup face images.