SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising

TL;DR

SSUMamba introduces a memory-efficient spatial-spectral state space model for hyperspectral image denoising, leveraging long-range dependencies and local modeling to outperform transformer-based methods in accuracy and efficiency.

Contribution

The paper proposes SSUMamba, a novel memory-efficient spatial-spectral state space model that enhances hyperspectral image denoising by exploiting long-range dependencies and local features.

Findings

Achieves superior denoising performance compared to transformer-based methods.

Uses less memory per batch while maintaining high accuracy.

Effectively models long-range spatial-spectral dependencies.

Abstract

Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but often comes with high computational complexity. Based on the state space model (SSM), Mamba is known for its remarkable long-range dependency modeling capabilities and computational efficiency. Building on this, we introduce a memory-efficient spatial-spectral UMamba (SSUMamba) for HSI denoising, with the spatial-spectral continuous scan (SSCS) Mamba being the core component. SSCS Mamba alternates the row, column, and band in six different orders to generate the sequence and uses the bidirectional SSM to exploit long-range spatial-spectral dependencies. In each order, the images are rearranged between adjacent scans to ensure spatial-spectral continuity. Additionally, 3D convolutions are embedded into the SSCS Mamba to enhance local spatial-spectral modeling. Experiments demonstrate that SSUMamba achieves superior denoising results with lower memory consumption per batch compared to transformer-based methods. The source code is available at https://github.com/lronkitty/SSUMamba.