Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space

TL;DR

This paper introduces a method to age or de-age faces in the StyleGAN2 latent space while preserving identity, using a simple model and feature selection, enabling reliable synthetic face generation for various applications.

Contribution

It presents a novel approach to manipulate face age in StyleGAN2's latent space with identity preservation, avoiding complex conditioning methods.

Findings

Empirically identifies identity-preserving subspace in StyleGAN2

Proposes a formula for safe aging/de-aging parameter limits

Creates a synthetic face dataset for benchmarking and research

Abstract

Face aging or de-aging with generative AI has gained significant attention for its applications in such fields like forensics, security, and media. However, most state of the art methods rely on conditional Generative Adversarial Networks (GANs), Diffusion-based models, or Visual Language Models (VLMs) to age or de-age faces based on predefined age categories and conditioning via loss functions, fine-tuning, or text prompts. The reliance on such conditioning leads to complex training requirements, increased data needs, and challenges in generating consistent results. Additionally, identity preservation is rarely taken into accountor evaluated on a single face recognition system without any control or guarantees on whether identity would be preserved in a generated aged/de-aged face. In this paper, we propose to synthesize aged and de-aged faces via editing latent space of StyleGAN2 using a simple support vector modeling of aging/de-aging direction and several feature selection approaches. By using two state-of-the-art face recognition systems, we empirically find the identity preserving subspace within the StyleGAN2 latent space, so that an apparent age of a given face can changed while preserving the identity. We then propose a simple yet practical formula for estimating the limits on aging/de-aging parameters that ensures identity preservation for a given input face. Using our method and estimated parameters we have generated a public dataset of synthetic faces at different ages that can be used for benchmarking cross-age face recognition, age assurance systems, or systems for detection of synthetic images. Our code and dataset are available at the project page https://www.idiap.ch/paper/agesynth/