Face Aging via Diffusion-based Editing
It addresses the problem of limited age range and large age gaps in face aging for applications like entertainment or forensics, but is incremental as it builds on existing diffusion models.
The paper tackles face aging by generating past or future facial images with age-related changes, proposing FADING, a diffusion-based editing method that outperforms existing approaches in aging accuracy, attribute preservation, and quality.
In this paper, we address the problem of face aging: generating past or future facial images by incorporating age-related changes to the given face. Previous aging methods rely solely on human facial image datasets and are thus constrained by their inherent scale and bias. This restricts their application to a limited generatable age range and the inability to handle large age gaps. We propose FADING, a novel approach to address Face Aging via DIffusion-based editiNG. We go beyond existing methods by leveraging the rich prior of large-scale language-image diffusion models. First, we specialize a pre-trained diffusion model for the task of face age editing by using an age-aware fine-tuning scheme. Next, we invert the input image to latent noise and obtain optimized null text embeddings. Finally, we perform text-guided local age editing via attention control. The quantitative and qualitative analyses demonstrate that our method outperforms existing approaches with respect to aging accuracy, attribute preservation, and aging quality.