Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions

Recently, hyperspectral image (HSI) super-resolution (SR) techniques based on deep learning have been actively developed. However, most hyperspectral image super-resolution reconstruction methods usually use all spectral bands simultaneously, leading to a mismatch of spectral properties between reconstructed HSI bands. Therefore, we proposed a new method of spatial-spectral dual path residual network (SGDPRN) based on spectral response function (SRF) to address the above problem. The SGDPRN is composed of the SRF guided grouping part, the spatial-spectral feature extraction part, and the final reconstruction part. Firstly, the reconstructed features for different spectral ranges are identified separately using SRF as a guide. Then, based on the grouping results, a spatial-spectral dual-path residual block is used to explore the spatial and spectral features by the designed parallel structure simultaneously. The spatial path is designed to extract sharp edges and realistic textures, and the spectral path is designed to model inter-spectral correlations to refine spectral features. At last, the third block of SGDPRN concatenates features of all groups and finishes the reconstruction of HSISR. QUST-1 satellite images have been applied in experiments, and the results showed that SGDPRN produced a higher peak signal to noise ratio, structural similarity metric, correlation coefficient, and lower spectral angle mapper, root mean square error than the other methods. This demonstrates that our method can effectively maintain the correlation of spectral bands while improving the spatial resolution.