DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Zhiliang, Zeng, Tao, Yang, Tao, Luo, Guoliang, Zeng, Jiyong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912634898481152
author Zhu, Zhiliang
Zeng, Tao
Yang, Tao
Luo, Guoliang
Zeng, Jiyong
author_facet Zhu, Zhiliang
Zeng, Tao
Yang, Tao
Luo, Guoliang
Zeng, Jiyong
contents Image deraining is crucial for improving visual quality and supporting reliable downstream vision tasks. Although Mamba-based models provide efficient sequence modeling, their limited ability to capture fine-grained details and lack of frequency-domain awareness restrict further improvements. To address these issues, we propose DeRainMamba, which integrates a Frequency-Aware State-Space Module (FASSM) and Multi-Directional Perception Convolution (MDPConv). FASSM leverages Fourier transform to distinguish rain streaks from high-frequency image details, balancing rain removal and detail preservation. MDPConv further restores local structures by capturing anisotropic gradient features and efficiently fusing multiple convolution branches. Extensive experiments on four public benchmarks demonstrate that DeRainMamba consistently outperforms state-of-the-art methods in PSNR and SSIM, while requiring fewer parameters and lower computational costs. These results validate the effectiveness of combining frequency-domain modeling and spatial detail enhancement within a state-space framework for single image deraining.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06746
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining
Zhu, Zhiliang
Zeng, Tao
Yang, Tao
Luo, Guoliang
Zeng, Jiyong
Computer Vision and Pattern Recognition
Image deraining is crucial for improving visual quality and supporting reliable downstream vision tasks. Although Mamba-based models provide efficient sequence modeling, their limited ability to capture fine-grained details and lack of frequency-domain awareness restrict further improvements. To address these issues, we propose DeRainMamba, which integrates a Frequency-Aware State-Space Module (FASSM) and Multi-Directional Perception Convolution (MDPConv). FASSM leverages Fourier transform to distinguish rain streaks from high-frequency image details, balancing rain removal and detail preservation. MDPConv further restores local structures by capturing anisotropic gradient features and efficiently fusing multiple convolution branches. Extensive experiments on four public benchmarks demonstrate that DeRainMamba consistently outperforms state-of-the-art methods in PSNR and SSIM, while requiring fewer parameters and lower computational costs. These results validate the effectiveness of combining frequency-domain modeling and spatial detail enhancement within a state-space framework for single image deraining.
title DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.06746