Self-Supervised Face Image Restoration with a One-Shot Reference
This work addresses a specific issue in face image restoration for applications requiring accurate semantic preservation, representing an incremental improvement over prior generative model-based methods.
The paper tackles the problem of semantic ambiguity in face image restoration by introducing a semantic-aware latent space exploration method that uses a one-shot reference to guide restoration, achieving superior performance in producing high-resolution, realistic images with correct semantics.
For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are susceptible to semantic ambiguity, particularly with images that have obviously correct semantics such as facial images. In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR). By explicitly modeling semantics information from a given reference image, SAIR is able to reliably restore severely degraded images not only to high-resolution and highly realistic looks but also to correct semantics. Quantitative and qualitative experiments collectively demonstrate the superior performance of the proposed SAIR. Our code is available at https://github.com/Liamkuo/SAIR.