Taking advantage of GANs enables to reconstruct SR images with high-frequency details and high perceptual quality. GAN based approach usually consists of Single Image Super Resolution (SISR) is a generator and a discriminator. Discriminator try to a very active research field. This paper identify HR or SR image whereas generator try to fool addresses SISR by using GAN-based approach discriminator to classify its generated SR image as with dual discriminators and incorporate HR image. SRGAN [3] employs an adversarial loss with attention mechanism. The experimental term to increase visually pleasing quality. SRFeat [7] results show that GDCA can used two discriminators and adopts the adversarial generate sharper and high pleasing images loss terms in both image and feature domains, resulting compare to other conventional methods.

To start with, a very early solution was the method of interpolation in image processing. Here, the low resolution image is resized by a factor of 2x or 4x using some interpolation method like nearest-neighbor, bilinear or bicubic method of interpolation. "Interpolation works by using known data to estimate values at unknown points. Image interpolation works in two directions, and tries to achieve a best approximation of a pixel's intensity based on the values at surrounding pixels." As from above illustration it is very clear that is resultant image is blurred and unrealistic.