GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention

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.