Lightweight Multi-Dilated Transformer for Image Deblurring

Abstract

Window-based Transformers have achieved promising results in image deblurring. However, their limited ability to capture nonlocal information hinders further improvement in deblurring performance. In this article, we develop an effective multi-dilated Transformer, named MDFormer, to address this issue. Specifically, we first develop a multi-dilated feature aggregation (MDFA) module, which aims to extract and aggregate nonlocal information with reduced computational costs. As commonly used feed-forward networks are pixelwise operations, we propose a dilated feed-forward network (DiFFN) module to enhance the information interaction between pixels further. Moreover, to fully utilize the features of different scales, we introduce a multiscale feature fusion (MSFF) module to provide improved guidance for image reconstruction. Extensive experiments demonstrate that the proposed method generates comparable results against state-of-the-art approaches with reduced computational costs.