Image Deraining with Frequency-Enhanced State Space Model

TL;DR

This paper introduces a novel frequency-enhanced state space model for image deraining, combining frequency domain processing with state space modeling and a mixed-scale gated convolutional block to effectively remove rain streaks.

Contribution

The study proposes the Deraining Frequency-Enhanced State Space Model (DFSSM) with deraining-specific enhancements and a mixed-scale gated convolutional block, advancing the effectiveness of rain removal in images.

Findings

Outperforms state-of-the-art deraining methods on synthetic datasets.

Effectively captures multi-scale rain streaks with the mixed-scale gated convolution.

Demonstrates robustness on real-world rainy images.

Abstract

Removing rain degradations in images is recognized as a significant issue. In this field, deep learning-based approaches, such as Convolutional Neural Networks (CNNs) and Transformers, have succeeded. Recently, State Space Models (SSMs) have exhibited superior performance across various tasks in both natural language processing and image processing due to their ability to model long-range dependencies. This study introduces SSM to image deraining with deraining-specific enhancements and proposes a Deraining Frequency-Enhanced State Space Model (DFSSM). To effectively remove rain streaks, which produce high-intensity frequency components in specific directions, we employ frequency domain processing concurrently with SSM. Additionally, we develop a novel mixed-scale gated-convolutional block, which uses convolutions with multiple kernel sizes to capture various scale degradations effectively and integrates a gating mechanism to manage the flow of information. Finally, experiments on synthetic and real-world rainy image datasets show that our method surpasses state-of-the-art methods. Code is available at https://github.com/ShugoYamashita/DFSSM.