Spectral Super Resolution of Hyperspectral Images via Coupled Dictionary Learning

Adversarial Spectral Super-Resolution for Multispectral Imagery Using Spatial Spectral Feature Attention Module

“…The reconstruction from multispectral to hyperspectral remote sensing imagery mostly are based on sparse representation. Fotiadou et al [40] introduced the coupled dictionary learning technique based on the ADMMs [41] to tackle the SSR problem on remote sensing imagery, but the pixel-wise operation neglects the correlation of neighboring pixels leading to poor generalization in other datasets. Yi et al [42] involved spatial constraint as a spatial preservation strategy to ensure the spatial consistency of MSI and HSI based on the spectral improvement approach, whereas multiple dictionaries were trained and the steps for reconstruction were complicated.…”

Computational approaches for sub-meter ocean color remote sensing

“…Just like in the spatial resolution case, in coupled dictionary learning correlations between the low spectral resolution data and high spectral resolution data are learned from a sample dataset, and then applied to the low spectral resolution data to achieve high spectral resolution estimates. A coupled dictionary learning approach was successfully applied to terrestrial remote sensing data by learning correlations between satellite sensors with different spectral resolutions [Fotiadou et al, 2019]. In addition to being proven on terrestrial targets, dictionary based-learning has also been applied to ocean color remote sensing, where the spectral resolution was increased by assuming sparsity of the components [Charles et al, 2014].…”

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

“…In [30], a 1D-CNN is designed with tunable spectral sub-sampling layer and in loss function not only the Euclidean distances are constrained but also the first and second derivatives. [15,19,46] enhance spectral resolution by dictionary learning and spectral sparse. In [15], the authors adopt coupled dictionary learning along with sparse representations based on the assumption that the sparse codes in MSI and HSI are the same.…”

“…[15,19,46] enhance spectral resolution by dictionary learning and spectral sparse. In [15], the authors adopt coupled dictionary learning along with sparse representations based on the assumption that the sparse codes in MSI and HSI are the same. Yi et al use both the spectral improvement and the spatial preservation strategies to enhance the spectral information while retaining the spatial one for HSI reconstruction [19].…”

“…In remote sensing imaging, the spectral and spatial resolutions restrict each other under the same imaging time due to the architectural constraints of the imaging system [15]. Many RGB or MSI images with high spatial resolution usually lack spectral information.…”