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

2025-08-12

AI Summary

Existing generative face aging/youngening methods rely on conditional GANs, diffusion models, or vision-language models, suffering from complex training procedures, high data demands, weak identity preservation, and limited evaluation protocols. To address these issues, this paper proposes a condition-free linear editing framework in the StyleGAN2 latent space. It first models age progression directions via support vector regression and identifies an identity-preserving subspace through multi-strategy feature selection. An empirical formula is then derived to control aging intensity while ensuring identity consistency. Extensive evaluation on two state-of-the-art face recognition (FR) systems demonstrates significant improvements in identity fidelity of edited faces. Furthermore, we introduce AgeSynth—a large-scale synthetic dataset spanning the full human age spectrum—open-sourced to support benchmarking in cross-age FR, age verification, and synthetic image detection.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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/

Problem

• Achieve identity-preserving face aging and de-aging in StyleGAN2
• Overcome reliance on complex conditioning in generative AI methods
• Ensure identity consistency across aging using face recognition systems

Innovation

• Editing StyleGAN2 latent space for aging
• Identity-preserving subspace with face recognition
• Simple formula for aging parameter limits