Learning Face Age Progression: A Pyramid Architecture of GANs
This work improves face age progression for applications like forensics or entertainment by enhancing realism and identity stability, though it is incremental as it builds on existing GAN methods.
The paper tackles the problem of generating realistic age-progressed face images by addressing aging accuracy and identity preservation, achieving state-of-the-art results with vivid aging effects as shown in visual and quantitative evaluations.
The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. In this paper, we present a novel generative adversarial network based approach. It separately models the constraints for the intrinsic subject-specific characteristics and the age-specific facial changes with respect to the elapsed time, ensuring that the generated faces present desired aging effects while simultaneously keeping personalized properties stable. Further, to generate more lifelike facial details, high-level age-specific features conveyed by the synthesized face are estimated by a pyramidal adversarial discriminator at multiple scales, which simulates the aging effects in a finer manner. The proposed method is applicable to diverse face samples in the presence of variations in pose, expression, makeup, etc., and remarkably vivid aging effects are achieved. Both visual fidelity and quantitative evaluations show that the approach advances the state-of-the-art.