EESAGAN: Edge-Enhanced and Structure-Aware GAN for Remote Sensing Image Super-Resolution

Remote sensing (RS) images often suffer from spatial resolution degradation and edge blurring due to sensor limitations and complex degradation factors such as atmospheric turbulence and motion. These issues negatively impact subsequent tasks like classification and detection. Most existing super-resolution (SR) methods rely on synthetic low-resolution(LR) data generated by bicubic interpolation, which fails to reflect real degradation processes, resulting in limited performance in practical applications. Furthermore, many methods insufficiently exploit high-frequency details and lack the ability to effectively model both global context and local structures. To address these challenges, this paper proposes an edge-enhanced SR framework for remote sensing images. A more realistic degradation model is constructed by estimating blur kernels from real LR images. The Edge-Enhanced and Structure-Aware Generative Adversarial Network (EESAGAN) is designed, incorporating the edge prior enhancement module (EPE), the edge-aware local attention module(ELAM), and the dynamic feature space attention module(DFSA). The edge-guided loss is also introduced to enhance image sharpness and perceptual consistency. Experimental results demonstrate that the proposed method achieves superior performance in PSNR, SSIM, and ERGAS compared to existing SR approaches.