Discriminator of ESRGAN based on Squeeze-and-Excitation Block and Inception Module for Qualitative Image

GAN models in super-resolution technology have garnered significant attention across various fields. The restoration of more natural and realistic textures is remarkably demonstrated, when converting low-resolution images to high-resolution counterparts. However, the traditional GAN models for super-resolution still face limitations in precisely reconstructing detailed characteristics such as textures, edges, and patterns when generating high-resolution images. This paper proposes a novel discriminator architecture that integrates the Inception module and SE Block to enhance the performance of super-resolution generative models, particularly the ESRGAN. This model is able to learn multi-scale image features and focus on critical information more effectively. The proposed model achieves performance improvements over the existing ESRGAN model, with a PSNR of 29.07 dB, SSIM of 0.82, LPIPS of 0.27, and NIQE of 5.85 on image quality evaluation metrics.