Uma Shanker Tiwary
Department of Information Technology, Indian Institute of Information Technology Allahabad, Prayagraj-211015
This report discusses the problem of denoising in image processing and the application of Generative Adversarial Networks (GANs) to address this challenge. GANs have demonstrated promising results in denoising tasks by learning to generate clean images from noisy ones through training on paired noisy and clean image datasets. Several variations of GANs have been proposed for denoising, including SRGAN, DCGAN, and LSGAN, each with unique strengths and weaknesses. This report suggests conducting a comparative study to determine the best-performing model under different conditions. The comparative study involves evaluating the denoising performance of these GAN models on a shared dataset, using metrics such as Peak Signal-to-Noise Ratio (PSNR). Through this paper we want to present you a comparative study on denoising images using SRGAN, DCGAN, Auto encoding GAN, Vanila GAN, and LSGAN to provide insights into the strengths and limitations of each model and the main aim of this study is to provide a guide to the best way to denoise the images.