Hyperspectral image reconstruction improved by adaptive manifold learning

Manifold Prior Guided Deep Unfolding for Hyperspectral Image Reconstruction

Computer Vision and Pattern Recognition

Summary

Hyperspectral images contain lots of color and light information that helps in many fields, but reconstructing them well can be hard. The authors found current methods struggle to adapt to the different spectral bands and to capture global spatial and spectral relationships effectively. They introduced a new approach that learns the underlying structure of the data and uses that knowledge to guide the reconstruction process in two key steps, improving accuracy and efficiency. Their method works better than existing ones on both simulated and real images.

What this means in practice

  • For remote sensing teams: Improve accuracy of hyperspectral data reconstruction for environmental monitoring and land use analysis.
  • For medical imaging developers: Enhance hyperspectral image clarity in medical diagnostics by better handling spectral variations and spatial features.

Authors

Shuqi Liu, Yingkai Zhang, Lin Gu, Tao Zhang, Ying Fu

Abstract

Hyperspectral Image (HSI) reconstruction has made substantial progress with the deep unfolding framework by decomposing the problem into a projection module and a denoiser module. Nevertheless, existing methods still exhibit limitations of insufficient matching with HSI data. The issues lie in two aspects: 1) the data-consistency projection module applies a fixed gradient descent step while ignoring the spectral content adaptivity of HSI; 2) the denoiser module either suffers from high computational complexity or is limited to the local receptive field, failing to efficiently capture the global spatial-spectral dependencies. In this paper, we propose a deep unfolding framework centered on a two-stage manifold learning strategy to obtain a degradation-free structural prior, which is then strategically injected into both the projection and denoiser modules. In the data-consistency projection, a prior-guided spectral weight mechanism is introduced to adaptively modulate the weight of spectral band. In the denoiser module, a manifold-guided Mamba is proposed to achieve the structure-aware extraction of spatial-spectral features through prior modulation. Quantitative and visual comparisons on synthetic and real-world datasets show that the proposed method significantly outperforms existing state-of-the-art approaches, while maintaining the structural interpretability of the unfolding framework. The code is available at https://github.com/SqLiu67/MPG-DU.