Reference-Guided Identity Preserving Face Restoration
This work addresses the problem of identity preservation in face restoration for applications like photo enhancement, though it appears incremental by building on existing reference-based methods.
The paper tackles the challenge of preserving face identity in diffusion-based image restoration by maximizing reference face utility, achieving state-of-the-art identity preserving restoration on benchmarks like FFHQ-Ref and CelebA-Ref-Test.
Preserving face identity is a critical yet persistent challenge in diffusion-based image restoration. While reference faces offer a path forward, existing reference-based methods often fail to fully exploit their potential. This paper introduces a novel approach that maximizes reference face utility for improved face restoration and identity preservation. Our method makes three key contributions: 1) Composite Context, a comprehensive representation that fuses multi-level (high- and low-level) information from the reference face, offering richer guidance than prior singular representations. 2) Hard Example Identity Loss, a novel loss function that leverages the reference face to address the identity learning inefficiencies found in the existing identity loss. 3) A training-free method to adapt the model to multi-reference inputs during inference. The proposed method demonstrably restores high-quality faces and achieves state-of-the-art identity preserving restoration on benchmarks such as FFHQ-Ref and CelebA-Ref-Test, consistently outperforming previous work.