Low Resolution Hyperspectral Image Research Articles

Thangka Hyperspectral Image Super-Resolution Based on a Spatial–Spectral Integration Network

Thangka refers to a form of Tibetan Buddhist painting on a fabric, scroll, or Thangka, often depicting deities, scenes, or mandalas. Deep-learning-based super-resolution techniques have been applied to improve the spatial resolution of hyperspectral images (HSIs), especially for the preservation and analysis of Thangka cultural heritage. However, existing CNN-based methods encounter difficulties in effectively preserving spatial information, due to challenges such as registration errors and spectral variability. To overcome these limitations, we present a novel cross-sensor super-resolution (SR) framework that utilizes high-resolution RGBs (HR-RGBs) to enhance the spectral features in low-resolution hyperspectral images (LR-HSIs). Our approach utilizes spatial–spectral integration (SSI) blocks and spatial–spectral restoration (SSR) blocks to effectively integrate and reconstruct spatial and spectral features. Furthermore, we introduce a frequency multi-head self-attention (F-MSA) mechanism that treats high-, medium-, and low-frequency features as tokens, enabling self-attention computations across the frequency dimension. We evaluate our method on a custom dataset of ancient Thangka paintings and demonstrate its effectiveness in enhancing the spectral resolution in high-resolution hyperspectral images (HR-HSIs), while preserving the spatial characteristics of Thangka artwork with minimal information loss.

RGB‐guided hyperspectral image super‐resolution with deep progressive learning

AbstractDue to hardware limitations, existing hyperspectral (HS) camera often suffer from low spatial/temporal resolution. Recently, it has been prevalent to super‐resolve a low resolution (LR) HS image into a high resolution (HR) HS image with a HR RGB (or multispectral) image guidance. Previous approaches for this guided super‐resolution task often model the intrinsic characteristic of the desired HR HS image using hand‐crafted priors. Recently, researchers pay more attention to deep learning methods with direct supervised or unsupervised learning, which exploit deep prior only from training dataset or testing data. In this article, an efficient convolutional neural network‐based method is presented to progressively super‐resolve HS image with RGB image guidance. Specifically, a progressive HS image super‐resolution network is proposed, which progressively super‐resolve the LR HS image with pixel shuffled HR RGB image guidance. Then, the super‐resolution network is progressively trained with supervised pre‐training and unsupervised adaption, where supervised pre‐training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes. The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral‐spatial constraint. It has a good generalisation capability, especially for blind HS image super‐resolution. Comprehensive experimental results show that the proposed deep progressive learning method outperforms the existing state‐of‐the‐art methods for HS image super‐resolution in non‐blind and blind cases.

AOHSR: attention mechanism-based optical image-guided hyperspectral image super-resolution

ABSTRACT With the rapid development of hyperspectral imaging technology, hyperspectral image (HSI) has been applied in various fields. However, due to the constraint of hyperspectral imaging devices, the spatial resolution of HSI remains too low to accurately meet the needs of target detection and recognition, which shackles the further application of HSI. In this paper, an optical image-guided HSISR algorithm based on the attention mechanism (AOHSR) was proposed in order to effectively improve the resolution of HSI. With the help of the attention mechanism, the proposed algorithm can effectively retain the spectral information of HSI and the spatial information of the optical image. Even without high spatial resolution optical imaging in the test stage, favourable reconstruction results can still be achieved. Firstly, the framework of the proposed optical image-guided HSI SR algorithm based on the attention mechanism was introduced. The algorithm consists of three modules: spectral reservation module (SRM), optical image guidance module (OIGM) and spatial-spectral recovery module (SSRM). The SRM uses an improved channel attention mechanism to extract spectral features from low-resolution (LR) HSIs to preserve spectral information. Through an improved spatial attention mechanism, the OIGM extracts spatial information from high-resolution (HR) optical images, supplementing the information extracted from LR HSI. The SSRM is used to fuse the spectral information on HSI and the spatial information on optical images to reconstruct HR HSI. Then, a joint training algorithm for reconstruction loss and optical image content loss was also proposed, which can effectively guide to learn the reconstruction of detailed information of the spatial texture while ensuring the preservation of spectral information. The results of experiments on three open datasets reveal that the HSIs reconstructed by the proposed network performed better than the existing algorithms regardless of whether optical images in the test stage exist.

GuidedNet: A General CNN Fusion Framework via High-Resolution Guidance for Hyperspectral Image Super-Resolution

Hyperspectral image super-resolution (HISR) is about fusing a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HR-MSI) to generate a high-resolution hyperspectral image (HR-HSI). Recently, convolutional neural network (CNN)-based techniques have been extensively investigated for HISR yielding competitive outcomes. However, existing CNN-based methods often require a huge amount of network parameters leading to a heavy computational burden, thus, limiting the generalization ability. In this article, we fully consider the characteristic of the HISR, proposing a general CNN fusion framework with high-resolution guidance, called GuidedNet. This framework consists of two branches, including 1) the high-resolution guidance branch (HGB) that can decompose the high-resolution guidance image into several scales and 2) the feature reconstruction branch (FRB) that takes the low-resolution image and the multiscaled high-resolution guidance images from the HGB to reconstruct the high-resolution fused image. GuidedNet can effectively predict the high-resolution residual details that are added to the upsampled HSI to simultaneously improve spatial quality and preserve spectral information. The proposed framework is implemented using recursive and progressive strategies, which can promote high performance with a significant network parameter reduction, even ensuring network stability by supervising several intermediate outputs. Additionally, the proposed approach is also suitable for other resolution enhancement tasks, such as remote sensing pansharpening and single-image super-resolution (SISR). Extensive experiments on simulated and real datasets demonstrate that the proposed framework generates state-of-the-art outcomes for several applications (i.e., HISR, pansharpening, and SISR). Finally, an ablation study and more discussions assessing, for example, the network generalization, the low computational cost, and the fewer network parameters, are provided to the readers. The code link is: https://github.com/Evangelion09/GuidedNet.

A survey of hyperspectral image super-resolution method

A survey of hyperspectral image super-resolution method

RGB-Induced Feature Modulation Network for Hyperspectral Image Super-Resolution

Super-resolution (SR) is one of the powerful techniques to improve image quality for low-resolution (LR) hyperspectral image (HSI) with insufficient detail and noise. Traditional methods typically perform simple cascade or addition during the fusion of the auxiliary high-resolution RGB and LR HSI. As a result, the abundant HR RGB details are not utilized as a priori information to enhance the HSI feature representation, leaving room for further improvements. To address this issue, we propose an RGB-induced feature modulation network for HSI SR (IFMSR). Considering that similar patterns are common in images, a multi-corresponding patch aggregation is designed to globally assemble this contextual information, which is beneficial for feature learning. Besides, to adequately exploit plentiful HR RGB details, an RGB-induced detail enhancement (RDE) module and a deep cross-modality feature modulation (CFM) module are proposed to transfer the supplementary materials from RGB to HSI. These modules can provide a more direct and instructive representation, leading to further edge recovery. Experiments on several datasets demonstrate that our approach achieves comparable performance under more realistic degradation condition. Our code is publicly available at https://github.com/qianngli/IFMSR.

HMFT: Hyperspectral and Multispectral Image Fusion Super-Resolution Method Based on Efficient Transformer and Spatial-Spectral Attention Mechanism.

Due to the imaging mechanism of hyperspectral images, the spatial resolution of the resulting images is low. An effective method to solve this problem is to fuse the low-resolution hyperspectral image (LR-HSI) with the high-resolution multispectral image (HR-MSI) to generate the high-resolution hyperspectral image (HR-HSI). Currently, the state-of-the-art fusion approach is based on convolutional neural networks (CNN), and few have attempted to use Transformer, which shows impressive performance on advanced vision tasks. In this paper, a simple and efficient hybrid architecture network based on Transformer is proposed to solve the hyperspectral image fusion super-resolution problem. We use the clever combination of convolution and Transformer as the backbone network to fully extract spatial-spectral information by taking advantage of the local and global concerns of both. In order to pay more attention to the information features such as high-frequency information conducive to HR-HSI reconstruction and explore the correlation between spectra, the convolutional attention mechanism is used to further refine the extracted features in spatial and spectral dimensions, respectively. In addition, considering that the resolution of HSI is usually large, we use the feature split module (FSM) to replace the self-attention computation method of the native Transformer to reduce the computational complexity and storage scale of the model and greatly improve the efficiency of model training. Many experiments show that the proposed network architecture achieves the best qualitative and quantitative performance compared with the latest HSI super-resolution methods.

Hyperspectral Image Superresolution via Subspace-Based Deep Prior Regularization

Hyperspectral imaging is able to provide a finer delivery of various material properties than conventional imaging systems. Yet in reality, an optical system can only generate data with high spatial resolution but low spectral one, or vice versa, at video rates. As a result, an issue that fuses low-resolution hyperspectral (LRHS) and high-resolution multispectral (HRMS) images has gained great attention. However, most fusion approaches depend purely on hand-crafted regularizers or data-driven priors, leading to the issues of tricky parameter selection or poor interpretability. In this work, a subspace-based deep prior regularization (SDPR) is proposed to tackle these problems, which takes both hand-crafted regularizer and data-driven prior into account. Specifically, we leverage the spectral correlation of the images and transfer them from the original space to the subspace domain, within which a modified U-net-based deep prior learning network (SDPL-net) is designed for the fusion issue. Moreover, instead of taking the output of SDPL-net directly as the result, we further feed the output back to the model-based optimization. Under such prior regularization, the recovered high-resolution hyperspectral (HRHS) image holds a high consistency to its inherent structure and hence tends to present enhanced reliability and accuracy. Experimental results on simulated and real data reveal that the proposed method excels other state-of-the-art (SOTA) methods in both quantitative and qualitative metrics.

Dynamical Fusion Model With Joint Variational and Deep Priors for Hyperspectral Image Super-Resolution

In this paper, we propose a novel dynamic fusion model (DFM) with joint variational and deep priors for the task of hyperspectral image super-resolution (HISR). The given model can benefit from both the advantages of traditional modeling and deep learning methods, thus achieving significant improvements based on existing deep pre-trained models. Specifically, the given model mainly contains two new designed terms, i.e., the weighted spatial fidelity (WSF) term and the deep fusion (DF) term. The WSF term focuses on the spatial recovery of the low-resolution hyperspectral image through the high-resolution multispectral image without the knowledge of the spectral response matrix, thus the proposed DFM can be viewed as a semi-blind model for HISR. Moreover, the DF term relied upon deep fusion with a designed adaptive weight matrix, which can effectively inject the deep priors into the traditional minimization model. Besides, the proposed DFM can be quickly and effectively solved using the alternating direction method of multipliers. Experimental results on widely used datasets demonstrate the superiority of our approach compared with state-of-the-art HISR methods.

Bayesian Nonlocal Patch Tensor Factorization for Hyperspectral Image Super-Resolution.

The synthesis of high-resolution (HR) hyperspectral image (HSI) by fusing a low-resolution HSI with a corresponding HR multispectral image has emerged as a prevalent HSI super-resolution (HSR) scheme. Recent researches have revealed that tensor analysis is an emerging tool for HSR. However, most off-the-shelf tensor-based HSR algorithms tend to encounter challenges in rank determination and modeling capacity. To address these issues, we construct nonlocal patch tensors (NPTs) and characterize low-rank structures with coupled Bayesian tensor factorization. It is worth emphasizing that the intrinsic global spectral correlation and nonlocal spatial similarity can be simultaneously explored under the proposed model. Moreover, benefiting from the technique of automatic relevance determination, we propose a hierarchical probabilistic framework based on Canonical Polyadic (CP) factorization, which incorporates a sparsity-inducing prior over the underlying factor matrices. We further develop an effective expectation-maximization-type optimization scheme for framework estimation. In contrast to existing works, the proposed model can infer the latent CP rank of NPT adaptively without tuning parameters. Extensive experiments on synthesized and real datasets illustrate the intrinsic capability of our model in rank determination as well as its superiority in fusion performance.

Hyperspectral Image Super-Resolution via Deep Spatiospectral Attention Convolutional Neural Networks.

Hyperspectral images (HSIs) are of crucial importance in order to better understand features from a large number of spectral channels. Restricted by its inner imaging mechanism, the spatial resolution is often limited for HSIs. To alleviate this issue, in this work, we propose a simple and efficient architecture of deep convolutional neural networks to fuse a low-resolution HSI (LR-HSI) and a high-resolution multispectral image (HR-MSI), yielding a high-resolution HSI (HR-HSI). The network is designed to preserve both spatial and spectral information thanks to a new architecture based on: 1) the use of the LR-HSI at the HR-MSI's scale to get an output with satisfied spectral preservation and 2) the application of the attention and pixelShuffle modules to extract information, aiming to output high-quality spatial details. Finally, a plain mean squared error loss function is used to measure the performance during the training. Extensive experiments demonstrate that the proposed network architecture achieves the best performance (both qualitatively and quantitatively) compared with recent state-of-the-art HSI super-resolution approaches. Moreover, other significant advantages can be pointed out by the use of the proposed approach, such as a better network generalization ability, a limited computational burden, and the robustness with respect to the number of training samples. Please find the source code and pretrained models from https://liangjiandeng.github.io/Projects_Res/HSRnet_2021tnnls.html.

Hierarchical spatio-spectral fusion for hyperspectral image super resolution via sparse representation and pre-trained deep model

Fusing a hyperspectral image (HSI) with a high resolution multispectral image (MSI) has been a highly attractive and effective approach for improving the spatial resolution of HSIs. However, most existing spatio-spectral fusion methods directly accomplish such a fusion process on the desired image scale. This limits the accuracy of the resulting model, especially when large magnification factors are involved. In this paper, a new dual pyramid model is proposed to implement hyperspectral image super resolution, based on a novel hierarchical spatial and spectral fusion method, in an effort to estimate the high resolution image progressively. In particular, an input low resolution HSI is upscaled progressively using a pre-trained deep Laplacian pyramid network, while the corresponding high resolution MSI is down sampled with multiple pyramid layers, forming a dual pyramid model. At each pyramid layer, the HSI and the MSI within the current layer are fused via sparse representation. Systematic qualitative and quantitative evaluations against benchmark datasets demonstrate that this new approach outperforms a number of spatio-spectral fusion based super resolution techniques, achieving outstanding performance over large scale factors.

Deep Self-Supervised Hyperspectral Image Reconstruction

Reconstructing a high-resolution hyperspectral (HR-HS) image via merging a low-resolution hyperspectral (LR-HS) image and a high-resolution RGB (HR-RGB) image has become a hot research topic, and can greatly benefit for different subsequent high-level vision tasks. Recently, deep learning–based approaches have evolved for HS image reconstruction and validated impressive performance. However, to learn a good reconstruction model in the deep learning–based methods, it is mandatory to previously collect large-scale training triplets consisting of the LR-HS, HR-RGB, and HR-HS images, which is difficult to be collected in real applications. This study proposes a deep self-supervised HS image reconstruction framework (DSSH), which does not have to depend on any handcrafted prior and previously collected training triplets at all. The proposed DSSH method leverages the designed network architecture itself for capturing the prior of the underlying structure in the latent HR-HS image and employs the observed LR-HS and HR-RGB images only for network parameter learning. Experiments on two benchmark HS image datasets validated that the proposed DSSH method manifests very impressive reconstruction performance, and is even better than some state-of-the-art supervised learning approaches.

An Unsupervised Cascade Fusion Network for Radiometrically-Accurate Vis-NIR-SWIR Hyperspectral Sharpening

Hyperspectral sharpening has been considered an important topic in many earth observation applications. Many studies have been performed to solve the Visible-Near-Infrared (Vis-NIR) hyperpectral sharpening problem, but there is little research related to hyperspectral sharpening including short-wave infrared (SWIR) bands despite many hyperspectral imaging systems capturing this wavelength range. In this paper, we introduce a novel method to achieve full-spectrum hyperspectral sharpening by fusing the high-resolution (HR) Vis-NIR multispectral image (MSI) and the Vis-NIR-SWIR low-resolution (LR) hyperspectral image (HSI). The novelty of the proposed approach lies in three points. Firstly, our model is designed for sharpening the full-spectrum HSI with high radiometric accuracy. Secondly, unlike most of the big-dataset-driven deep learning models, we only need one LR-HSI and HR-MSI pair for training. Lastly, per-pixel classification is implemented to test the spectral accuracy of the results.

Hyperspectral image super-resolution based on the transfer of both spectra and multi-level features.

Existing hyperspectral image (HSI) super-resolution methods fusing a high-resolution RGB image (HR-RGB) and a low-resolution HSI (LR-HSI) always rely on spatial degradation and handcrafted priors, which hinders their practicality. To address these problems, we propose a novel, to the best of our knowledge, method with two transfer models: a window-based linear mixing (W-LM) model and a feature transfer model. Specifically, W-LM initializes a high-resolution HSI (HR-HSI) by transferring the spectra from the LR-HSI to the HR-RGB. By using the proposed feature transfer model, the HR-RGB multi-level features extracted by a pre-trained convolutional neural network (CNN) are then transferred to the initialized HR-HSI. The proposed method fully exploits spectra of LR-HSI and multi-level features of HR-RGB and achieves super-resolution without requiring the spatial degradation model and any handcrafted priors. The experimental results for 32 × super-resolution on two public datasets and our real image set demonstrate the proposed method outperforms eight state-of-the-art existing methods.

Semi-blind hyperspectral and multispectral image fusion based on a non-factorization model

Fusion of low-resolution hyperspectral images (LR-HSI) with high-resolution multispectral images (HR-MSI) is currently the most cost-effective method for acquiring high-resolution hyperspectral images (HR-HSI). The existing fusion models like spectral unmixing, matrix-factorization, and tensor-factorization require decomposing the target HR-HSI into multiple factor matrices or tensors before fusion. Usually requires a large number of variable optimization processes. So, the above approaches do not apply to the arguably real-time scenario. Moreover, the miscellaneous intermediate estimates render poor fusion stability. This paper proposes a novel non-factorization model to address the above problems. The model firstly gets access to a rough estimate of HR-HSI through the Moore–Penrose inverse operation. Then, we acquire the further HR-HSI forecast according to the correlation between the target HR-HSI and LR-HSI singular values through the coupled singular value decomposition (SVD) of the rough HR-HSI and LR-HIS. Finally, we obtain the precise HR-HSI estimates via the multiplicative update rule. Our proposed model directly estimates the target HR-HSI, reduces the estimation process of intermediate variables, effectively saves calculation time, and enhances the stability of the fusion. We conduct experiments on remote sensing, ground-based, and real datasets to validate our proposed model’s real-time and stability.

Heterogeneity-Aware Recurrent Neural Network for Hyperspectral and Multispectral Image Fusion

Due to the hardware limitations of remote imaging sensors, it is challenging to acquire images with high resolution in both the spatial and spectral domains. An effective and economical way to obtain high-resolution hyperspectral images (HR HSI) is to fuse low-resolution hyperspectral images (LR HSI) and high-resolution multispectral images (HR MSI). However, most existing deep learning based fusion methods employ the same network for all of the spectra without exploring their complex regional heterogeneity of hyperspectral characteristics. Taking various intrinsic spatial and spectral characteristics across different pixels into consideration, this paper proposes a mixture of recurrent neural networks (RNNs) under the variational probabilistic framework for spatial and spectral resolution enhancement. More specifically, we firstly cluster spectral characteristics into different groups, and employ different RNN experts for various spectra generation under the guidance of clustering. Moreover, a cluster-specific learnable Gaussian prior is proposed to provide a prior knowledge of heterogeneity. Further, an online variational inference scheme is derived for end-to-end optimization. Extensive experimental results demonstrate the effectiveness and efficiency of the proposed model on both synthetic and real datasets, compared with state-of-the-art unsupervised fusion methods.

Unsupervised Super Resolution Network for Hyperspectral Histologic Imaging.

Hyperspectral imaging (HSI) has many advantages in microscopic applications, including high sensitivity and specificity for cancer detection on histological slides. However, acquiring hyperspectral images of a whole slide with a high image resolution and a high image quality can take a long scanning time and require a very large data storage. One potential solution is to acquire and save low-resolution hyperspectral images and reconstruct the high-resolution ones only when needed. The purpose of this study is to develop a simple yet effective unsupervised super resolution network for hyperspectral histologic imaging with the guidance of RGB digital histology images. High-resolution hyperspectral images of hemoxylin & eosin (H&E) stained slides were obtained at 10× magnification and down-sampled 2×, 4×, and 5× to generate low-resolution hyperspectral data. High-resolution digital histologic RGB images of the same field of view (FOV) were cropped and registered to the corresponding high-resolution hyperspectral images. A neural network based on a modified U-Net architecture, which takes the low-resolution hyperspectral images and high-resolution RGB images as inputs, was trained with unsupervised methods to output high-resolution hyperspectral data. The generated high-resolution hyperspectral images have similar spectral signatures and improved image contrast than the original high-resolution hyperspectral images, which indicates that the super resolution network with RGB guidance can improve the image quality. The proposed method can reduce the acquisition time and save storage space taken up by hyperspectral images without compromising image quality, which will potentially promote the use of hyperspectral imaging technology in digital pathology and many other clinical applications.

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

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 and the reconstruction accuracy of the HR HSI relies heavily on the registration accuracy of different modalities. This paper exploits the uncharted problem domain of HSI-SR without the requirement of multi-modality registration. Given the unregistered LR HSI and HR MSI with overlapped regions, we design a unique unsupervised learning structure linking the two unregistered modalities by projecting them into the same statistical space through the same encoder. The mutual information (MI) is further adopted to capture the non-linear statistical dependencies between the representations from two modalities (carrying spatial information) and their raw inputs. By maximizing the MI, spatial correlations between different modalities can be well characterized to further reduce the spectral distortion. A collaborative $l_{2,1}$ norm is employed as the reconstruction error instead of the more common $l_2$ norm, so that individual pixels can be recovered as accurately as possible. With this design, the network allows to extract correlated spectral and spatial information from unregistered images that better preserves the spectral information. The proposed method is referred to as unregistered and unsupervised mutual Dirichlet Net ($u^2$-MDN). Extensive experimental results using benchmark HSI datasets demonstrate the superior performance of $u^2$-MDN as compared to the state-of-the-art.

A Deep Framework for Hyperspectral Image Fusion Between Different Satellites.

Recently, fusing a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) of different satellites has become an effective way to improve the resolution of an HSI. However, due to different imaging satellites, different illumination, and adjacent imaging time, the LR-HSI and HR-MSI may not satisfy the observation models established by existing works, and the LR-HSI and HR-MSI are hard to be registered. To solve the above problems, we establish new observation models for LR-HSIs and HR-MSIs from different satellites, then a deep-learning-based framework is proposed to solve the key steps in multi-satellite HSI fusion, including image registration, blur kernel learning, and image fusion. Specifically, we first construct a convolutional neural network (CNN), called RegNet, to produce pixel-wise offsets between LR-HSI and HR-MSI, which are utilized to register the LR-HSI. Next, according to the new observation models, a tiny network, called BKLNet, is built to learn the spectral and spatial blur kernels, where the BKLNet and RegNet can be trained jointly. In the fusion part, we further train a FusNet by downsampling the registered data with the learned spatial blur kernel. Extensive experiments demonstrate the superiority of the proposed framework in HSI registration and fusion accuracy.