GuidedNet: A General CNN Fusion Framework via High-Resolution Guidance for Hyperspectral Image Super-Resolution

• Published in: IEEE transactions on cybernetics Vol. 53; no. 7; pp. 4148 - 4161
• Main Authors: Ran, Ran, Deng, Liang-Jian, Jiang, Tai-Xiang, Hu, Jin-Fan, Chanussot, Jocelyn, Vivone, Gemine
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Artificial Intelligence; Artificial neural networks; Computer Science; Computing costs; Convolutional neural network (CNN); High resolution; high-resolution guidance; hyperspectral image super-resolution (HISR); Hyperspectral imaging; Image enhancement; image fusion; Image reconstruction; Image resolution; Pansharpening; Parameters; Remote sensing; single-image super-resolution (SISR); Spatial resolution; Superresolution; Task analysis; Training

Hyperspectral image super-resolution (HISR) is about fusing a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HR-MSI) to generate a high-resolution hyperspectral image (HR-HSI). Recently, convolutional neural network (CNN)-based techniques have been extensively...