Deep Blind Hyperspectral Image Super-Resolution

Zhang, Lei; Nie, Jiangtao; Wei, Wei; Li, Yong; Zhang, Yanning

doi:10.1109/tnnls.2020.3005234

Cited by 79 publications

(38 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the previous means, more HSI SR methods use other images with high spatial resolution and make full use of the spatial information [34,35]. On this basis, some research base on the sparsity of HSI [21,24,[35][36][37][38] to reconstruct the HR-HSI; some authors study on the selfsimilarity between local and nonlocal patches [25,[34][35][36] and the low rank of them [38][39][40]; some literatures have use or model the imaging principles and degradation process for super-resolution [24,41,42]. From the perspective of the solution process: dictionary-based methods are common such as [25,38,39].…”

Section: A Hyperspectral Image Super-resolutionmentioning

confidence: 99%

“…Since HSI is a 3D-tensor, Xu et al provide a t-product [35] to establish the relationship between HR-HSI and LR-HSI and constraint nonlocal similarity, Li et al [37] propose a fusion method based on Coupled Sparse Tensor Decomposition (CSTF), Dian et al compose 4D-Tensor with similar HSI patches [40], and transform HSI SR problem into LTTR regularization constraint by using low-rank property. In [41,42], CNN is used to fit the reconstruction process, and in [41] GAN [43] is adopted for SR. Kwon and Tai [21] guide the up-sampling process of LR-HSI by RGB and spectrum substitution to refine the upsampled spectra. Borsoi et al [44] adopt spectral unmixing and model the spectral variability to study the SR problem of seasonal variation.…”

Section: A Hyperspectral Image Super-resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Remote Sensing Imagery Generation From RGB Images Based on Joint Discrimination

Liu

Lei

Shi

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

Section: A Hyperspectral Image Super-resolutionmentioning

confidence: 99%

Section: A Hyperspectral Image Super-resolutionmentioning

confidence: 99%

Hyperspectral Remote Sensing Imagery Generation From RGB Images Based on Joint Discrimination

Liu

Lei

Shi

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In recent years, there have been several attempts which fuse a high resolution multispectral image (HRMSI) with a low resolution hyperspectral image (LRHSI) [1][2][3][4][5][6][7][8][9][10][11][12][13] to produce a high spatio-spectral resolution HSI. Basically, all fusion approaches can be grouped in the following categories: methods using a Bayesian framework [6,11,[14][15][16][17][18], matrix factorization based methods [4,5,12,[19][20][21], tensor factorization based methods [1,3,9,[22][23][24][25] and deep learning based methods [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral and Multispectral Image Fusion Using Coupled Non-Negative Tucker Tensor Decomposition

et al. 2021

View full text Add to dashboard Cite

Fusing a low spatial resolution hyperspectral image (HSI) with a high spatial resolution multispectral image (MSI), aiming to produce a super-resolution hyperspectral image, has recently attracted increasing research interest. In this paper, a novel approach based on coupled non-negative tensor decomposition is proposed. The proposed method performs a tucker tensor factorization of a low resolution hyperspectral image and a high resolution multispectral image under the constraint of non-negative tensor decomposition (NTD). The conventional matrix factorization methods essentially lose spatio-spectral structure information when stacking the 3D data structure of a hyperspectral image into a matrix form. Moreover, the spectral, spatial, or their joint structural features have to be imposed from the outside as a constraint to well pose the matrix factorization problem. The proposed method has the advantage of preserving the spatio-spectral structure of hyperspectral images. In this paper, the NTD is directly imposed on the coupled tensors of the HSI and MSI. Hence, the intrinsic spatio-spectral structure of the HSI is represented without loss, and spatial and spectral information can be interdependently exploited. Furthermore, multilinear interactions of different modes of the HSIs can be exactly modeled with the core tensor of the Tucker tensor decomposition. The proposed method is straightforward and easy to implement. Unlike other state-of-the-art approaches, the complexity of the proposed approach is linear with the size of the HSI cube. Experiments on two well-known datasets give promising results when compared with some recent methods from the literature.

show abstract

“…They treat the fusion of LR HSI and HR MSI as an ill-posed inverse problem. Equations are first established by observation model [21][22][23] and then constrained by many handcraft priors. Popular priors contain the sparse prior [16,18,19] and lowrankness prior [24,25].…”

Section: Introductionmentioning

confidence: 99%

“…These equations are solved by iterative optimization methods such as alternating direction method of multipliers (ADMM) [26] and gradient descent algorithm [27]. Dictionary learning methods [22,23] are a representative kind of VM-based methods. By using sparse representation, they can combine the dictionaries from LR HSI and the high-resolution sparse coefficients from HR MSI to obtain HR HSI.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral and Multispectral Image Fusion by Deep Neural Network in a Self-Supervised Manner

Gao

Jiang

2021

Remote Sensing

View full text Add to dashboard Cite

Compared with multispectral sensors, hyperspectral sensors obtain images with high- spectral resolution at the cost of spatial resolution, which constrains the further and precise application of hyperspectral images. An intelligent idea to obtain high-resolution hyperspectral images is hyperspectral and multispectral image fusion. In recent years, many studies have found that deep learning-based fusion methods outperform the traditional fusion methods due to the strong non-linear fitting ability of convolution neural network. However, the function of deep learning-based methods heavily depends on the size and quality of training dataset, constraining the application of deep learning under the situation where training dataset is not available or of low quality. In this paper, we introduce a novel fusion method, which operates in a self-supervised manner, to the task of hyperspectral and multispectral image fusion without training datasets. Our method proposes two constraints constructed by low-resolution hyperspectral images and fake high-resolution hyperspectral images obtained from a simple diffusion method. Several simulation and real-data experiments are conducted with several popular remote sensing hyperspectral data under the condition where training datasets are unavailable. Quantitative and qualitative results indicate that the proposed method outperforms those traditional methods by a large extent.

show abstract

Deep Blind Hyperspectral Image Super-Resolution

Cited by 79 publications

References 52 publications

Hyperspectral Remote Sensing Imagery Generation From RGB Images Based on Joint Discrimination

Hyperspectral Remote Sensing Imagery Generation From RGB Images Based on Joint Discrimination

Hyperspectral and Multispectral Image Fusion Using Coupled Non-Negative Tucker Tensor Decomposition

Hyperspectral and Multispectral Image Fusion by Deep Neural Network in a Self-Supervised Manner

Contact Info

Product

Resources

About