Hyperspectral Image Superresolution Using Global Gradient Sparse and Nonlocal Low-Rank Tensor Decomposition With Hyper-Laplacian Prior

• Main Authors: Yidong Peng, Weisheng Li, Xiaobo Luo, Jiao Du
• Format: Article
• Language: English
• Published: IEEE 2021-01-01
• Series: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
• Subjects: Global gradient sparse; hyper-Laplacian; hyperspectral image; nonlocal low-rank; superresolution; total variation
• Online Access: https://ieeexplore.ieee.org/document/9417623/

This article presents a novel global gradient sparse and nonlocal low-rank tensor decomposition model with a hyper-Laplacian prior for hyperspectral image (HSI) superresolution to produce a high-resolution HSI (HR-HSI) by fusing a low-resolution HSI (LR-HSI) with an HR multispectral image (HR-MSI). Inspired by the investigated hyper-Laplacian distribution of the gradients of the difference images between the upsampled LR-HSI and latent HR-HSI, we formulate the relationship between these two datasets as a <inline-formula><tex-math notation="LaTeX">$\ell _{p}$</tex-math></inline-formula> <inline-formula><tex-math notation="LaTeX">$(0 &lt; p &lt; 1)$</tex-math></inline-formula>-norm term to enforce spectral preservation. Then, the relationship between the HR-MSI and latent HR-HSI is built using a tensor-based fidelity term to recover the spatial details. To effectively capture the high spatio-spectral-nonlocal similarities of the latent HR-HSI, we design a novel nonlocal low-rank Tucker decomposition to model the 3-D regular tensors constructed from the grouped nonlocal similar HR-HSI cubes. The global spatial-spectral total variation regularization is then adopted to ensure the global spatial piecewise smoothness and spectral consistency of the reconstructed HR-HSI from nonlocal low-rank cubes. Finally, an alternating direction method of multipliers-based algorithm is designed to efficiently solve the optimization problem. Experiments on both the synthetic and real datasets collected by different sensors show the effectiveness of the proposed method, from visual and quantitative assessments.