GF2Hyper dataset for training and test

GF2Hyper dataset involves Panchromatic/Multispectral imager carried on Gaofen-1 and Hyperion sensor on EO-1 satellite. Gaofen-1 is a Chinese satellite employed two imagers, which can obtain 8 m resolution multispectral images with four bands and a 2 m resolution PAN image that covered the full spectral ranges of corresponding multispectral images, from 450 to 900 nm. Images obtained by Hyperion are with a spatial resolution of 30 meters and obtain 242 bands from 357 to 2567 nm. In this dataset, we only select 148 useful bands. GF2Hyper dataset is used to verify the one situation of generalized spectral super-resolution, i.e., PansSR. PansSR is to achieve the joint enhancement of spatial resolution and spectral resolution using auxiliary higher-resolution spectral channels, usually, panchromatic images. The file named "GF2Hyper_train.h5" contains 1152 training samples where the high-resolution PAN images are with size of 128×128×1 while the size of multispectral images is 32×32×4. Moreover, we also give some test images in the "GF2Hyper_test.mat". Details about generalized spectral super-resolution can be found in the following paper. Paper: J. He, Q. Yuan, J. Li, and L. Zhang, "PoNet: A universal physical optimization-based spectral super-resolution network for arbitrary multispectral images," Information Fusion, vol. 80, pp. 205–225, 2022. More information about the author can be found at https://jianghe96.github.io/ If this dataset is helpful please cite as: @article{He2022PoNet,
title={PoNet: A universal physical optimization-based spectral super-resolution network for arbitrary multispectral images},
author={He, Jiang and Yuan, Qiangqiang and Li, Jie and Zhang, Liangpei},
journal={Information Fusion},
volume={80},
pages={205--225},
year={2022},
}