A convex formulation for hyperspectral image superresolution via subspace-based regularization

Abstract

Hyperspectral remote sensing images (HSIs) usually have high spectral resolution and low spatial resolution. Conversely, multispectral images (MSIs) usually have low spectral and high spatial resolutions. The problem of inferring images which combine the high spectral and high spatial resolutions of HSIs and MSIs, respectively, is a data fusion problem that has been the focus of recent active research due to the increasing availability of HSIs and MSIs retrieved from the same geographical area. We formulate this problem as the minimization of a convex objective function containing two quadratic data-fitting terms and an edge-preserving regularizer. The data-fitting terms account for blur, different resolutions, and additive noise. The regularizer, a form of vector Total Variation, promotes piecewise-smooth solutions with discontinuities aligned across the hyperspectral bands. The downsampling operator accounting for the different spatial resolutions, the non-quadratic and non-smooth nature of the regularizer, and the very large size of the HSI to be estimated lead to a hard optimization problem. We deal with these difficulties by exploiting the fact that HSIs generally "live" in a low-dimensional subspace and by tailoring the Split Augmented Lagrangian Shrinkage Algorithm (SALSA), which is an instance of the Alternating Direction Method of Multipliers (ADMM), to this optimization problem, by means of a convenient variable splitting. The spatial blur and the spectral linear operators linked, respectively, with the HSI and MSI acquisition processes are also estimated, and we obtain an effective algorithm that outperforms the state-of-the-art, as illustrated in a series of experiments with simulated and real-life data.

IEEE Trans. Geosci. Remote Sens., to be published

References in corpus (2)

• An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems
• Deconvolving Images with Unknown Boundaries Using the Alternating Direction Method of Multipliers

Cited by in corpus (52)

• Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation
• Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
• Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-Resolution
• Multi-Band Image Fusion Based on Spectral Unmixing
• Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution
• R-FUSE: Robust Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation
• Learned Spectral Super-Resolution
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning
• FusionMamba: Efficient Remote Sensing Image Fusion with State Space Model
• Hyperspectral Super-Resolution with Coupled Tucker Approximation: Recoverability and SVD-based algorithms
• Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling
• Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net
• Coupled Tensor Decomposition for Hyperspectral and Multispectral Image Fusion with Inter-Image Variability
• Blind Image Fusion for Hyperspectral Imaging with the Directional Total Variation
• Hyperspectral Pansharpening: Critical Review, Tools and Future Perspectives
• Hyperspectral Super-Resolution via Global-Local Low-Rank Matrix Estimation
• A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution
• Unsupervised Hyperspectral Image Super-Resolution via Self-Supervised Modality Decoupling
• Fast and High-Quality Blind Multi-Spectral Image Pansharpening
• Simulated JWST datasets for multispectral and hyperspectral image fusion
• An inner-loop free solution to inverse problems using deep neural networks
• Multi-Resolution Beta-Divergence NMF for Blind Spectral Unmixing
• Hybrid Inexact BCD for Coupled Structured Matrix Factorization in Hyperspectral Super-Resolution
• Multisource and Multitemporal Data Fusion in Remote Sensing
• A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring
• Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
• Unmixing based PAN guided fusion network for hyperspectral imagery
• Scene-Adapted Plug-and-Play Algorithm with Guaranteed Convergence: Applications to Data Fusion in Imaging
• Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
• Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution
• Recent Advances and New Guidelines on Hyperspectral and Multispectral Image Fusion
• High-Order Coupled Fully-Connected Tensor Network Decomposition for Hyperspectral Image Super-Resolution
• Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization
• InverseNet: Solving Inverse Problems with Splitting Networks
• Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
• Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control
• Robust Hyperspectral Image Fusion with Simultaneous Guide Image Denoising via Constrained Convex Optimization
• Super-Resolution for Hyperspectral and Multispectral Image Fusion Accounting for Seasonal Spectral Variability
• Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part I: Methodology and Experiments
• Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part II: Theoretical Analysis
• Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation
• Subspace-Based Feature Fusion From Hyperspectral And Multispectral Image For Land Cover Classification
• Pansharpening of PRISMA products for archaeological prospection
• Self-Regression Learning for Blind Hyperspectral Image Fusion Without Label
• Super-resolution of THz time-domain images based on low-rank representation
• Hyperspectral Super-resolution: A Coupled Nonnegative Block-term Tensor Decomposition Approach
• Best of both worlds: Fusing hyperspectral data from two generations of spectro-imagers for X-ray astrophysics
• Blind Hyperspectral-Multispectral Image Fusion via Graph Laplacian Regularization
• Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution
• Fusing Multiple Multiband Images
• Robust Fusion of Multi-Band Images with Different Spatial and Spectral Resolutions for Change Detection
• Is There Any Recovery Guarantee with Coupled Structured Matrix Factorization for Hyperspectral Super-Resolution?