Identity-Preserving Aging of Face Images via Latent Diffusion Models
This work addresses the challenge of limited aging datasets for improving face recognition accuracy, representing a strong domain-specific advancement.
The paper tackled the problem of facial aging's impact on face recognition systems by proposing a latent diffusion model for synthetic aging and de-aging of face images, achieving a significant reduction of approximately 44% in False Non-Match Rate on benchmark datasets.
The performance of automated face recognition systems is inevitably impacted by the facial aging process. However, high quality datasets of individuals collected over several years are typically small in scale. In this work, we propose, train, and validate the use of latent text-to-image diffusion models for synthetically aging and de-aging face images. Our models succeed with few-shot training, and have the added benefit of being controllable via intuitive textual prompting. We observe high degrees of visual realism in the generated images while maintaining biometric fidelity measured by commonly used metrics. We evaluate our method on two benchmark datasets (CelebA and AgeDB) and observe significant reduction (~44%) in the False Non-Match Rate compared to existing state-of the-art baselines.