Real HSI-MSI-PAN image dataset for the hyperspectral/multi-spectral/panchromatic image fusion and super-resolution fields
This provides a real-world benchmark for researchers in hyperspectral image fusion, addressing a domain-specific need to reduce biases from inaccurate simulations.
The authors tackled the problem of unreliable simulated datasets in hyperspectral image fusion by releasing a real HSI/MSI/PAN image dataset that is spatially registered, aiming to improve algorithm credibility and fairness in comparisons.
Nowadays, most of the hyperspectral image (HSI) fusion experiments are based on simulated datasets to compare different fusion methods. However, most of the spectral response functions and spatial downsampling functions used to create the simulated datasets are not entirely accurate, resulting in deviations in spatial and spectral features between the generated images for fusion and the real images for fusion. This reduces the credibility of the fusion algorithm, causing unfairness in the comparison between different algorithms and hindering the development of the field of hyperspectral image fusion. Therefore, we release a real HSI/MSI/PAN image dataset to promote the development of the field of hyperspectral image fusion. These three images are spatially registered, meaning fusion can be performed between HSI and MSI, HSI and PAN image, MSI and PAN image, as well as among HSI, MSI, and PAN image. This real dataset could be available at https://aistudio.baidu.com/datasetdetail/281612. The related code to process the data could be available at https://github.com/rs-lsl/CSSNet.