Age Progression and Regression with Spatial Attention Modules
This addresses the challenge of realistic and efficient age transformation in face images for applications like entertainment or forensics, but it is incremental as it builds on existing cGAN methods.
The paper tackles the problems of requiring multiple models for different age mappings and poor photo-realism in age progression/regression by proposing a cGAN-based framework with separate generators and spatial attention mechanisms, achieving lifelike face image synthesis with personalized features preserved.
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.