Design of Super-Resolution Reconstruction Model for Airborne Remote Sensing Images

Sensor resolution, data acquisition conditions and multiple compression degradation of images during transmission often lead to quality degradation of remotely sensed images, which affects the fine analysis and identification of features. In order to improve the image resolution, this study adopts a blind super-resolution reconstruction method based on deep learning, proposes a super-resolution framework based on generative adversarial network (GAN), designs ARDB as the generator and U-Net as the discriminator, and explores the optimization strategy of the loss function. By constructing high-resolution and low-resolution paired remote sensing image datasets and implementing step-by-step training on the BasicSR platform, the model performance is finally evaluated by a variety of metrics, and the results show that the present model has a significant advantage over other super-resolution methods in terms of visual effect and quantitative evaluation.