Overview of remote sensing image fusion based on deep learning

With the widespread application and rapid development of remote sensing technology, the quality requirements for remote sensing images are gradually improving. Currently, relying solely on one sensor is difficult to ensure high signal-to- noise ratio while capturing images with high spatial and spectral resolution. Remote sensing image fusion technology obtains high-quality images by combining the spatial information and spectral (or spectral) information of different sensors. Meanwhile, in recent years, deep learning theory has developed rapidly and is widely applied in image processing such as remote sensing image fusion. Therefore, in order to gain a more systematic understanding of the current status of remote sensing image fusion based on deep learning and promote the development of remote sensing image fusion, this article first introduces commonly used remote sensing satellite images and traditional image fusion algorithms; Then, the remote sensing image fusion algorithm based on deep learning is emphasized, and the advantages and disadvantages of deep learning fusion methods (PanNet, LPPN, WSDFNet) are compared and analyzed; Finally, the future prospects of remote sensing image fusion methods based on deep learning are presented.