The use of a pretrained image classification model (trained on cats and dogs. for example) as a perceptual loss function for hyperspectral super-resolution and pansharpening tasks is surprisingly effective. However. RGB-based networks do not take full advantage of the spectral information in hyperspectral data. https://www.ealisboa.com/super-find-Care-Bears-Good-Luck-Bear-T-Shirt-great-choice/