Non-local blind hyperspectral image super-resolution via 4d sparse tensor factorization and low-rank
Non-local blind hyperspectral image super-resolution via 4d sparse tensor factorization and low-rank
复制标题
DOI：
10.3934/ipi.2020015
复制
发表时间：
2020
影响因子：
1.3
通讯作者：
Weihong Guo;Wei Wan;Jun Liu;Haiyang Huang
中科院分区：
文献类型：
--
作者：
Weihong Guo;Wei Wan;Jun Liu;Haiyang Huang
高光谱图像（HSI）超分辨率是一种提高高光谱图像空间分辨率以获得更好的视觉感知和下游应用的技术。这是一个非常不适定的逆问题，通常通过融合低分辨率（LR）多光谱图像和高分辨率（HR）多光谱图像来解决。在空间退化算子完全未知的情况下，盲HSI超分辨率问题更具挑战性。本文利用HSI的空间非局部自相似性和光谱全局相关性，提出了一种新的稀疏张量分解模型，用于盲HSI超分辨任务。采用图像聚类方法，收集一些相似的hsi三维立方体，这些立方体可以形成一些高相关性的四维图像聚类。我们采用聚类智能计算，不仅节省了计算时间，而且引入了源自立方体冗余的非局部正则性。利用张量分解的稀疏性和四维相似簇在非局部自相似方向上的低秩性，设计了一个保留hsi空间-光谱结构相关性的稀疏张量正则化项。此外，我们提出了一种基于近邻交替方向乘法器（ADMM）的算法来有效地求解所提出的模型。数值实验表明，该模型优于许多最先进的HSI超分辨率方法。
Hyperspectral image (HSI) super-resolution is a technique to improve the spatial resolution of a HSI for better visual perception and down stream applications. This is a very ill-posed inverse problem and is often solved by fusing the low-resolution (LR) HSI with a high-resolution (HR) multispectral image (MSI). It is more challenging for blind HSI super-resolution, i.e., when the spatial degradation operators are completely unknown. In this paper, we propose a novel sparse tensor factorization model for the task of blind HSI super-resolution using the spatial non-local self-similarity and spectral global correlation of HSIs. Image clustering method is employed to collect some similar 3D cubes of HSIs which can be formed as some 4D image clusters with high correlation. We conduct cluster wise computation to not only save computation time but also to introduce a non-local regularity originated from the redundancy of cubes. By using the sparsity of tensor decomposition and the low-rank in non-local self-similarity direction underlying 4D similar clusters, we design a sparse tensor regularization term, which preserves the spatial-spectral structural correlation of HSIs. In addition, we present a proximal alternating direction method of multipliers (ADMM) based algorithm to efficiently solve the proposed model. Numerical experiments demonstrate that the proposed model outperforms many state-of-the-art HSI super-resolution methods.