Face Aging With Conditional Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based method for automatic face aging that preserves individual identity, using a novel identity-preserving optimization approach, and demonstrates its effectiveness through objective evaluation with face recognition and age estimation tools.

Contribution

The paper presents a new GAN-based face aging technique that maintains identity, unlike previous methods, by optimizing latent vectors with a novel identity-preserving approach.

Findings

High-quality aged and rejuvenated face images produced.

Objective evaluations show strong identity preservation.

Method outperforms previous face aging approaches.

Abstract

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.