Accurate Image Restoration with Attention Retractable Transformer

TL;DR

The paper introduces the Attention Retractable Transformer (ART), a novel image restoration model combining dense and sparse attention modules to expand receptive fields and improve performance across multiple tasks.

Contribution

It proposes a new Transformer architecture with alternating dense and sparse attention modules for enhanced image restoration capabilities.

Findings

Outperforms state-of-the-art methods on super-resolution, denoising, and JPEG artifact reduction.

Provides wider receptive fields through sparse attention modules.

Achieves superior quantitative and visual results on benchmark datasets.

Abstract

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit self-attention computation within non-overlapping windows. However, each group of tokens are always from a dense area of the image. This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions. Obviously, this strategy could result in restricted receptive fields. To address this issue, we propose Attention Retractable Transformer (ART) for image restoration, which presents both dense and sparse attention modules in the network. The sparse attention module allows tokens from sparse areas to interact and thus provides a wider receptive field. Furthermore, the alternating application of dense and sparse attention modules greatly enhances representation ability of Transformer while providing retractable attention on the input image.We conduct extensive experiments on image super-resolution, denoising, and JPEG compression artifact reduction tasks. Experimental results validate that our proposed ART outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually. We also provide code and models at https://github.com/gladzhang/ART.