DBSAGAN: Dual Branch Split Attention Generative Adversarial Network for Super-Resolution Reconstruction in Remote Sensing Images

Super-resolution reconstruction methods emerge in an endless stream, but the models proposed by many researchers are not fit for certain types of images, such as remote sensing images. This is because remote sensing images have rich texture details and geometrical structures. Therefore, directly applying previous models to remote sensing images generates unsatisfactory artifacts. In this letter, we propose a dual branch split attention generative adversarial network (DBSAGAN) for super-resolution tasks on remote sensing images. Specifically, the proposed DBSAGAN adopts a dual branch split attention group as the cascading basic unit in the generator. In addition, we remove batch normalization layers in the basic unit to improve the generative ability of the network. To reduce the gap between the reconstructed and original images from the frequency domain, we innovatively use focal frequency loss to constrain the network. Experiments demonstrate that the proposed network outperforms existing state-of-the-art methods on the Gaofen-1 remote sensing image dataset.