Review of GAN-Based Image Super-Resolution Techniques

The objective of Image Super-Resolution (ISR), a significant area of study in computer vision and image processing, is to produce high-resolution images from low-resolution images. The main objective of this paper is to explore the Image Super-Resolution methods based on Generative Adversarial Networks (GANs), especially SRGAN and ESRGAN. In the experimental part, the performance of SRGAN and ESRGAN will be evaluated by using PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index) as evaluation metrics, and the results demonstrate the great potential of Generative Adversarial Networks in Image Super-Resolution tasks, especially in improving the quality of the generated images, and both SRGAN and ESRGAN perform well in recovering image details. Facing the current challenges, researchers can explore new methods and techniques to promote the development and application of image super-resolution technology. The prospect of wide application of GAN models in the field of image processing provides rich opportunities and possibilities for future research and innovation.