In plain words: A system that ages or rejuvenates a face by finding the right internal code so the result looks like the same person. Unlike earlier face-aging tricks that let identity drift, face-recognition and age-guessing checks showed the faces looked the right age and still matched.

Abstract · Face Aging With Conditional Generative Adversarial Networks

It has been recently shown that Generative Adversarial Networks (GANs) can produce synthetic images of exceptional visual fidelity. In this work, we propose the GAN-based method for automatic face aging. Contrary to previous works employing GANs for altering of facial attributes, we make a particular emphasize on preserving the original person's identity in the aged version of his/her face. To this end, we introduce a novel approach for "Identity-Preserving" optimization of GAN's latent vectors. The objective evaluation of the resulting aged and rejuvenated face images by the state-of-the-art face recognition and age estimation solutions demonstrate the high potential of the proposed method.

Grigory Antipov, Moez Baccouche, Jean-Luc Dugelay
arXiv:1702.01983 · cs.CV · submitted Feb 7, 2017 · updated May 30, 2017
abstract · pdf · html · 5 pages, 3 figures, accepted at ICIP 2017. With respect to v1: (1) changed the abbreviation of the main model from "acGAN" to "Age-cGAN" in order to avoid confusion with "Auxiliary Classifier Generative Adversarial Networks" introduced by Odena et al.; (2) corrected a typo in Formula 1