Emphasizing Crucial Features for Efficient Image Restoration

TL;DR

This paper introduces ECFNet, a novel image restoration framework that emphasizes crucial features through spatial and frequency attention mechanisms, effectively handling varying degradation levels across image regions.

Contribution

The paper proposes a new framework with spatial and frequency attention modules, a multi-scale block, and an integrated U-shaped network for improved image restoration performance.

Findings

ECFNet outperforms state-of-the-art methods on synthetic datasets.

The proposed attention mechanisms effectively identify and enhance degraded regions.

Multi-scale design captures global information for better restoration.

Abstract

Image restoration is a challenging ill-posed problem which estimates latent sharp image from its degraded counterpart. Although the existing methods have achieved promising performance by designing novelty architecture of module, they ignore the fact that different regions in a corrupted image undergo varying degrees of degradation. In this paper, we propose an efficient and effective framework to adapt to varying degrees of degradation across different regions for image restoration. Specifically, we design a spatial and frequency attention mechanism (SFAM) to emphasize crucial features for restoration. SFAM consists of two modules: the spatial domain attention module (SDAM) and the frequency domain attention module (FDAM). The SFAM discerns the degradation location through spatial selective attention and channel selective attention in the spatial domain, while the FDAM enhances high-frequency signals to amplify the disparities between sharp and degraded image pairs in the spectral domain. Additionally, to capture global range information, we introduce a multi-scale block (MSBlock) that consists of three scale branches, each containing multiple simplified channel attention blocks (SCABlocks) and a multi-scale feed-forward block (MSFBlock). Finally, we propose our ECFNet, which integrates the aforementioned components into a U-shaped backbone for recovering high-quality images. Extensive experimental results demonstrate the effectiveness of ECFNet, outperforming state-of-the-art (SOTA) methods on both synthetic and real-world datasets.