Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net

  title={Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net},
  author={Ying Qu and Hairong Qi and Chiman Kwan},
Hyperspectral images (HSI) provide rich spectral information that contributed to the successful performance improvement of numerous computer vision tasks. However, it can only be achieved at the expense of images' spatial resolution. Hyperspectral image super-resolution (HSI-SR) addresses this problem by fusing low resolution (LR) HSI with multispectral image (MSI) carrying much higher spatial resolution (HR). All existing HSI-SR approaches require the LR HSI and HR MSI to be well registered… Expand
Spatial Resolution Enhancement of Remote Sensing Hyperspectral Images With Localized Spatial-Spectral Dictionary Pair
A novel dictionary-based HSI and MSI fusion method (SSLDF method) is proposed in this paper, in which a localized spatial-spectral dictionary pair incorporating both spatial and spectral information simultaneously is constructed and adopted, rather than the traditional spectral or spatial one. Expand
Evaluation of Pan-Sharpening Techniques Using Lagrange Optimization
The paper presents an image fusion method based on pixel-level optimization using the Lagrange multiplier that is shown to outperform all the existing methods. Expand
An Improved Version of the Generalized Laplacian Pyramid Algorithm for Pansharpening
This work created and assessed a method for improving a widespread approach, based on the generalized Laplacian pyramid decomposition, by combining two different cost-effective upgrades: the estimation of the detail-extraction filter from data and the utilization of an improved injection scheme based on multilinear regression. Expand
A New Benchmark Based on Recent Advances in Multispectral Pansharpening: Revisiting Pansharpening With Classical and Emerging Pansharpening Methods
A new benchmark consisting of recent advances in MS pansharpening is proposed, and optimized classical approaches [multiresolution analysis (MRA) and component substitution (CS)] are compared with methods belonging to the third generation of panshARPening, represented by variational optimization-based (VO) and machine learning (ML) techniques. Expand
A Brief Review of Some Interesting Mars Rover Image Enhancement Projects
  • C. Kwan
  • Computer Science
  • Computers
  • 2021
This paper will address perceptually lossless compression of Mastcam images, debayering and resolution enhancement of Mast cam images, high resolution stereo and disparity map generation using fused Mastcam image, and improved performance of anomaly detection and pixel clustering using combined left and right Mastcam pictures. Expand


Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
  • Ying Qu, H. Qi, C. Kwan
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
This paper makes the first attempt to solving the HSI-SR problem using an unsupervised encoder-decoder architecture that carries the following uniquenesses: it is composed of two encoder and decoder networks, coupled through a shared decoder, in order to preserve the rich spectral information from the H SI network. Expand
Nonlocal Coupled Tensor CP Decomposition for Hyperspectral and Multispectral Image Fusion
Experimental results suggest that the proposed nonlocal tensor decomposition model for hyperspectral and multispectral image fusion (HSI-MSI fusion) substantially outperforms the existing state-of-the-art HSI- MSI fusion methods. Expand
Hyperspectral Image Super-Resolution With Optimized RGB Guidance
This paper presents a simple and efficient convolutional neural network (CNN) based method for HSI super-resolution in an unsupervised way, without any prior training, and append a CSR optimization layer onto the HSIsuper-resolution network to automatically select the best CSR in a given CSR dataset. Expand
Deep Hyperspectral Image Sharpening
A deep HSI sharpening method is presented for the fusion of an LR-HSI with an HR-MSI, which directly learns the image priors via deep convolutional neural network-based residual learning. Expand
Coupled Convolutional Neural Network With Adaptive Response Function Learning for Unsupervised Hyperspectral Super Resolution
This work proposes an unsupervised deep learning-based fusion method—HyCoNet—that can solve the problems in HSI–MSI fusion without the prior PSF and SRF information. Expand
A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based Regularization
The split augmented Lagrangian shrinkage algorithm (SALSA), which is an instance of the alternating direction method of multipliers (ADMM), is added to this optimization problem, by means of a convenient variable splitting, and an effective algorithm is obtained that outperforms the state of the art. Expand
Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation
  • W. Dong, Fazuo Fu, +4 authors Xin Li
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • 2016
A new hyperspectral image super-resolution method from a low-resolution (LR) image and a HR reference image of the same scene to improve the accuracy of non-negative sparse coding and to exploit the spatial correlation among the learned sparse codes. Expand
Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization
In the proposed CSTF method, an HR-HSI is considered as a 3D tensor and the fusion problem is redefined as the estimation of a core Tensor and dictionaries of the three modes, which demonstrates the superiority of this algorithm over the current state-of-the-art HSI-MSI fusion approaches. Expand
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
This paper constructs a novel MS/HS fusion model which takes the observation models of low-resolution images and the low-rankness knowledge along the spectral mode of HrHS image into consideration, and designs an iterative algorithm to solve the model by exploiting the proximal gradient method. Expand
Hyperspectral Images Super-Resolution via Learning High-Order Coupled Tensor Ring Representation
The proposed method first tensorizes the HSI to be estimated into a high-order tensor in which multiscale spatial structures and the original spectral structure are represented, and achieves the state-of-the-art super-resolution performance. Expand