Exploring high-quality image deraining Transformer via effective large kernel attention

Abstract

In recent years, Transformer has demonstrated significant performance in single image deraining tasks. However, the standard self-attention in the Transformer makes it difficult to model local features of images effectively. To alleviate the above problem, this paper proposes a high-quality deraining Transformer with effective large kernel attention, named as ELKAformer. The network employs the Transformer-Style Effective Large Kernel Conv-Block (ELKB), which contains 3 key designs: Large Kernel Attention Block (LKAB), Dynamical Enhancement Feed-forward Network (DEFN), and Edge Squeeze Recovery Block (ESRB) to guide the extraction of rich features. To be specific, LKAB introduces convolutional modulation to substitute vanilla self-attention and achieve better local representations. The designed DEFN refines the most valuable attention values in LKAB, allowing the overall design to better preserve pixel-wise information. Additionally, we develop ESRB to obtain long-range dependencies of different positional information. Massive experimental results demonstrate that this method achieves favorable effects while effectively saving computational costs. Our code is available at github