2024/06/02 by Muge Yan, Lizhi Wang, Yan, Muge +5
Computer Science · Mathematics · #Artificial intelligence #Computer science #Computer vision #Correlation #Geometry #Hyperspectral imaging #Image (mathematics) #Image and Signal Denoising Methods #Mathematics #Pattern recognition (psychology)
paper · pdf · doi:10.48550/arxiv.2406.00683
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. While most methods emphasize space-domain learning using image space priors like non-local similarity, frequency-domain learning using image frequency priors remains neglected, limiting the reconstruction capability of networks. In this paper, we first propose a Hyperspectral Frequency Correlation (HFC) prior rooted in in-depth statistical frequency analyses of existent HSI datasets. Leveraging the HFC prior, we subsequently establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF) targeting low-frequency and high-frequency components, respectively. The outputs of SAF and SIF are adaptively merged by a learnable gating filter, thus achieving a thorough exploitation of image frequency priors. Integrating the frequency domain learning and the existing space domain learning, we finally develop the Correlation-driven Mixing Domains Transformer (CMDT) for HSI reconstruction. Extensive experiments highlight that our method surpasses various state-of-the-art (SOTA) methods in reconstruction quality and computational efficiency.