Dilated Strip Attention Network for Image Restoration

TL;DR

This paper introduces a dilated strip attention network (DSAN) that enhances image restoration by capturing wider contextual information efficiently through a novel attention mechanism, outperforming existing methods.

Contribution

The paper proposes a dilated strip attention (DSA) mechanism for better contextual information gathering in image restoration, with multi-scale receptive fields for improved performance.

Findings

Outperforms state-of-the-art algorithms on multiple image restoration tasks.

Efficiently captures wider contextual information with fewer parameters.

Demonstrates the effectiveness of DSA in enhancing image restoration quality.

Abstract

Image restoration is a long-standing task that seeks to recover the latent sharp image from its deteriorated counterpart. Due to the robust capacity of self-attention to capture long-range dependencies, transformer-based methods or some attention-based convolutional neural networks have demonstrated promising results on many image restoration tasks in recent years. However, existing attention modules encounters limited receptive fields or abundant parameters. In order to integrate contextual information more effectively and efficiently, in this paper, we propose a dilated strip attention network (DSAN) for image restoration. Specifically, to gather more contextual information for each pixel from its neighboring pixels in the same row or column, a dilated strip attention (DSA) mechanism is elaborately proposed. By employing the DSA operation horizontally and vertically, each location can harvest the contextual information from a much wider region. In addition, we utilize multi-scale receptive fields across different feature groups in DSA to improve representation learning. Extensive experiments show that our DSAN outperforms state-of-the-art algorithms on several image restoration tasks.