HDMba: Hyperspectral Remote Sensing Imagery Dehazing with State Space Model

TL;DR

This paper introduces HDMba, a novel hyperspectral image dehazing network leveraging a specialized Mamba architecture with local-global spectral-spatial modeling, outperforming existing methods on a real dataset.

Contribution

The paper presents the first HSI dehazing network based on the Mamba model, incorporating a window selective scan module for enhanced local and global feature extraction.

Findings

HDMba outperforms state-of-the-art dehazing methods on Gaofen-5 dataset.

The WSSM improves local dependency capture in hyperspectral images.

The proposed method effectively reconstructs hazy hyperspectral scenes.

Abstract

Haze contamination in hyperspectral remote sensing images (HSI) can lead to spatial visibility degradation and spectral distortion. Haze in HSI exhibits spatial irregularity and inhomogeneous spectral distribution, with few dehazing networks available. Current CNN and Transformer-based dehazing methods fail to balance global scene recovery, local detail retention, and computational efficiency. Inspired by the ability of Mamba to model long-range dependencies with linear complexity, we explore its potential for HSI dehazing and propose the first HSI Dehazing Mamba (HDMba) network. Specifically, we design a novel window selective scan module (WSSM) that captures local dependencies within windows and global correlations between windows by partitioning them. This approach improves the ability of conventional Mamba in local feature extraction. By modeling the local and global spectral-spatial information flow, we achieve a comprehensive analysis of hazy regions. The DehazeMamba layer (DML), constructed by WSSM, and residual DehazeMamba (RDM) blocks, composed of DMLs, are the core components of the HDMba framework. These components effectively characterize the complex distribution of haze in HSIs, aiding in scene reconstruction and dehazing. Experimental results on the Gaofen-5 HSI dataset demonstrate that HDMba outperforms other state-of-the-art methods in dehazing performance. The code will be available at https://github.com/RsAI-lab/HDMba.