Age Progression and Regression with Spatial Attention Modules

TL;DR

This paper introduces a cGAN-based framework with spatial attention modules for simultaneous face age progression and regression, improving realism and preserving identity across diverse images.

Contribution

It proposes a dual-generator cGAN model with spatial attention to enhance face aging and rejuvenation, addressing limitations of multiple models and image variation issues.

Findings

Synthesizes realistic face images at target ages.

Preserves personalized features and identity.

Maintains age-irrelevant regions unchanged.

Abstract

Age progression and regression refers to aesthetically render-ing a given face image to present effects of face aging and rejuvenation, respectively. Although numerous studies have been conducted in this topic, there are two major problems: 1) multiple models are usually trained to simulate different age mappings, and 2) the photo-realism of generated face images is heavily influenced by the variation of training images in terms of pose, illumination, and background. To address these issues, in this paper, we propose a framework based on conditional Generative Adversarial Networks (cGANs) to achieve age progression and regression simultaneously. Particularly, since face aging and rejuvenation are largely different in terms of image translation patterns, we model these two processes using two separate generators, each dedicated to one age changing process. In addition, we exploit spatial attention mechanisms to limit image modifications to regions closely related to age changes, so that images with high visual fidelity could be synthesized for in-the-wild cases. Experiments on multiple datasets demonstrate the ability of our model in synthesizing lifelike face images at desired ages with personalized features well preserved, and keeping age-irrelevant regions unchanged.