Real HSI-MSI-PAN image dataset for the hyperspectral/multi-spectral/panchromatic image fusion and super-resolution fields
Shuangliang Li
TL;DR
The paper addresses the credibility gap in hyperspectral image fusion caused by reliance on simulated data with imperfect downsampling. It releases a real, spatially registered HSI/MSI/PAN dataset (ZY1-02D) that supports multiple fusion scenarios without synthetic spectral/spatial degradation models, enabling fair comparisons of fusion methods. Dataset details include HSI with 76 bands, MSI with 108 bands, and PAN at 2.5 m resolution, with corresponding image sizes from the ZY1-02D satellite, and accompanying data processing code. This resource is intended to standardize benchmarks and accelerate development in hyperspectral fusion by removing biases inherent to simulated datasets.
Abstract
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.