Super-Resolution (SR) refers to the reconstruction of high-resolution image from low-resolution image, which has important application value in object detection, medical imaging, satellite remote sensing and other fields. In recent years, with the rapid development of deep learning, the image super-resolution reconstruction method based on deep learning has made remarkable progress. In this paper, R-SRGAN (Residual Super-Resolution Generative Adversarial Networks) is used to build the model and realize image super-resolution. By adding residual blocks between adjacent convolutional layers of the GAN generator, more detailed information is retained. At the same time, the Wassertein distance is used as a loss function to enhance the training effect and achieve image super-resolution.