Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach

Abstract

Hyperspectral super-resolution refers to the problem of fusing a hyperspectral image (HSI) and a multispectral image (MSI) to produce a super-resolution image (SRI) that has fine spatial and spectral resolution. State-of-the-art methods approach the problem via low-rank matrix approximations to the matricized HSI and MSI. These methods are effective to some extent, but a number of challenges remain. First, HSIs and MSIs are naturally third-order tensors (data "cubes") and thus matricization is prone to loss of structural information--which could degrade performance. Second, it is unclear whether or not these low-rank matrix-based fusion strategies can guarantee identifiability or exact recovery of the SRI. However, identifiability plays a pivotal role in estimation problems and usually has a significant impact on performance in practice. Third, the majority of the existing methods assume that there are known (or easily estimated) degradation operators applied to the SRI to form the corresponding HSI and MSI--which is hardly the case in practice. In this work, we propose to tackle the super-resolution problem from a tensor perspective. Specifically, we utilize the multidimensional structure of the HSI and MSI to propose a coupled tensor factorization framework that can effectively overcome the aforementioned issues. The proposed approach guarantees the identifiability of the SRI under mild and realistic conditions. Furthermore, it works with little knowledge of the degradation operators, which is clearly an advantage over the existing methods. Semi-real numerical experiments are included to show the effectiveness of the proposed approach.

References in corpus (9)

• Tensor Decomposition for Signal Processing and Machine Learning
• A convex formulation for hyperspectral image superresolution via subspace-based regularization
• Hyperspectral and Multispectral Image Fusion based on a Sparse Representation
• Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation
• Nonlinear unmixing of hyperspectral images: models and algorithms
• Multi-Band Image Fusion Based on Spectral Unmixing
• Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering
• On Identifiability of Nonnegative Matrix Factorization
• Exploring multimodal data fusion through joint decompositions with flexible couplings

Cited by in corpus (31)

• Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution
• Spectrum Cartography via Coupled Block-Term Tensor Decomposition
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning
• Hyperspectral Super-Resolution with Coupled Tucker Approximation: Recoverability and SVD-based algorithms
• Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling
• Coupled Tensor Decomposition for Hyperspectral and Multispectral Image Fusion with Inter-Image Variability
• Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
• Tensor Completion from Regular Sub-Nyquist Samples
• A Tensor Factorization Method for 3D Super-Resolution with Application to Dental CT
• Hyperspectral Super-Resolution via Global-Local Low-Rank Matrix Estimation
• Blind Direction-of-Arrival Estimation in Acoustic Vector-Sensor Arrays via Tensor Decomposition and Kullback-Leibler Divergence Covariance Fitting
• Unsupervised Hyperspectral Image Super-Resolution via Self-Supervised Modality Decoupling
• A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
• mHealth hyperspectral learning for instantaneous spatiospectral imaging of hemodynamics
• Multi-Resolution Beta-Divergence NMF for Blind Spectral Unmixing
• Hybrid Inexact BCD for Coupled Structured Matrix Factorization in Hyperspectral Super-Resolution
• A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring
• Personalized Coupled Tensor Decomposition for Multimodal Data Fusion: Uniqueness and Algorithms
• Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
• Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution
• High-Order Coupled Fully-Connected Tensor Network Decomposition for Hyperspectral Image Super-Resolution
• Recent Advances and New Guidelines on Hyperspectral and Multispectral Image Fusion
• PARAFAC2-based Coupled Matrix and Tensor Factorizations
• Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization
• MultiHU-TD: Multifeature Hyperspectral Unmixing Based on Tensor Decomposition
• Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
• Hyperspectral Super-resolution: A Coupled Nonnegative Block-term Tensor Decomposition Approach
• PARAFAC2-based Coupled Matrix and Tensor Factorizations with Constraints
• Blind Hyperspectral-Multispectral Image Fusion via Graph Laplacian Regularization
• Single Image Super-Resolution of Noisy 3D Dental CT Images Using Tucker Decomposition
• Infusing Learned Priors into Model-Based Multispectral Imaging