Locally Controlled Face Aging with Latent Diffusion Models
This work addresses the need for more personalized and realistic face aging in applications like entertainment or forensics, though it is incremental as it builds on existing latent diffusion models.
The paper tackles the problem of face aging by addressing the heterogeneous nature of aging across facial regions, using latent diffusion models to selectively age specific areas, resulting in more realistic and controllable aging with improved identity preservation and image fidelity.
We present a novel approach to face aging that addresses the limitations of current methods which treat aging as a global, homogeneous process. Existing techniques using GANs and diffusion models often condition generation on a reference image and target age, neglecting that facial regions age heterogeneously due to both intrinsic chronological factors and extrinsic elements like sun exposure. Our method leverages latent diffusion models to selectively age specific facial regions using local aging signs. This approach provides significantly finer-grained control over the generation process, enabling more realistic and personalized aging. We employ a latent diffusion refiner to seamlessly blend these locally aged regions, ensuring a globally consistent and natural-looking synthesis. Experimental results demonstrate that our method effectively achieves three key criteria for successful face aging: robust identity preservation, high-fidelity and realistic imagery, and a natural, controllable aging progression.