A STUDY ON FACE SUPER-RESOLUTION RECONSTRUCTION ALGORITHM BASED ON IMPROVED SRGAN

Abstract

In this paper, we propose a novel approach to address the challenges of Super-Resolution Generative Adversarial Network (SRGAN) in face image super-resolution reconstruction. We introduce a new improved SRGAN algorithm, named Wasserstein SRGAN (W-SRGAN), which addresses the limitations of the original model by enhancing the loss function, generator, and discriminator. Our approach utilizes the embedded residual structure combined with feature fusion as the new generator, while removing the Sigmoid of the last layer of the discriminator of SRGAN by borrowing the idea of Wasserstein GAN (W-GAN). Additionally, we replace the Kullback–Leibler (KL) divergence of SRGAN with Wasserstein distance. The contributions of our research are twofold. Firstly, we propose a new face super-resolution reconstruction algorithm that outperforms existing methods in terms of visual quality. Secondly, we introduce a new loss function and generator–discriminator architecture that can be applied to other image super-resolution tasks, extending the applicability of GANs in this domain. Experimental results demonstrate that our proposed W-SRGAN outperforms Bicubic, Super-Resolution Convolutional Neural Network (SRCNN), and SRGAN in terms of visual quality on all Celeb A datasets. These results confirm the effectiveness of our proposed algorithm and provide a new solution for face super-resolution reconstruction.