HSRMamba: Efficient Wavelet Stripe State Space Model for Hyperspectral Image Super-Resolution

TL;DR

HSRMamba is a novel hyperspectral image super-resolution model that combines wavelet decomposition and a strip-based scanning scheme to reduce artifacts, improve performance, and maintain computational efficiency.

Contribution

It introduces a strip-based scanning scheme and wavelet decomposition into the Visual Mamba framework, enhancing super-resolution quality and artifact reduction.

Findings

Outperforms existing methods in accuracy

Reduces computational load and model size

Achieves state-of-the-art results in hyperspectral super-resolution

Abstract

Single hyperspectral image super-resolution (SHSR) aims to restore high-resolution images from low-resolution hyperspectral images. Recently, the Visual Mamba model has achieved an impressive balance between performance and computational efficiency. However, due to its 1D scanning paradigm, the model may suffer from potential artifacts during image generation. To address this issue, we propose HSRMamba. While maintaining the computational efficiency of Visual Mamba, we introduce a strip-based scanning scheme to effectively reduce artifacts from global unidirectional scanning. Additionally, HSRMamba uses wavelet decomposition to alleviate modal conflicts between high-frequency spatial features and low-frequency spectral features, further improving super-resolution performance. Extensive experiments show that HSRMamba not only excels in reducing computational load and model size but also outperforms existing methods, achieving state-of-the-art results.