Boosting Image Restoration via Priors from Pre-trained Models

TL;DR

This paper introduces a lightweight refinement module that leverages pre-trained models to significantly improve various image restoration tasks, demonstrating effectiveness across multiple applications.

Contribution

It proposes the Pre-Train-Guided Refinement Module (PTG-RM), a novel approach that utilizes off-the-shelf features from pre-trained models to enhance low-level image restoration.

Findings

PTG-RM improves restoration performance across tasks.

The module has fewer than 1 million parameters.

Effective for low-light, deraining, deblurring, and denoising.

Abstract

Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions. Yet, their potential for low-level tasks such as image restoration remains relatively unexplored. In this paper, we explore such models to enhance image restoration. As off-the-shelf features (OSF) from pre-trained models do not directly serve image restoration, we propose to learn an additional lightweight module called Pre-Train-Guided Refinement Module (PTG-RM) to refine restoration results of a target restoration network with OSF. PTG-RM consists of two components, Pre-Train-Guided Spatial-Varying Enhancement (PTG-SVE), and Pre-Train-Guided Channel-Spatial Attention (PTG-CSA). PTG-SVE enables optimal short- and long-range neural operations, while PTG-CSA enhances spatial-channel attention for restoration-related learning. Extensive experiments demonstrate that PTG-RM, with its compact size ($<$1M parameters), effectively enhances restoration performance of various models across different tasks, including low-light enhancement, deraining, deblurring, and denoising.