Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN

In this paper, we present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. First, practical degradation model that considers various factors beyond downsampling. To the best of our knowledge, is first composite proposed radiographic images. Furthermore, propose AID-SRGAN, which can simultaneously denoise and generate high-resolution (HR) radiographs. model, introduce an attention mechanism into denoising module to make it more robust complicated degradation. Finally, SR reconstructs HR radiographs using “clean” low-resolution (LR) addition, separate-joint training approach train extensive experiments are conducted show method superior its counterparts. e.g., achieves 31.90 PSNR with scale factor $$4\times $$ , 7.05% higher than obtained by recent work, SPSR [16]. Our dataset code will be made available at: https://github.com/yongsongH/AIDSRGAN-MICCAI2022 .