Locally Controlled Face Aging with Latent Diffusion Models

TL;DR

This paper introduces a novel face aging method using latent diffusion models that allows for fine-grained, region-specific aging control, resulting in more realistic and personalized aging effects while preserving identity.

Contribution

It proposes a new approach leveraging latent diffusion models for region-specific face aging, addressing heterogeneity in facial aging and improving realism and control.

Findings

Effective region-specific aging control demonstrated

High fidelity and realistic aging results achieved

Preserves identity while enabling natural aging progression

Abstract

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.