Discriminator of ESRGAN based on Squeeze-and-Excitation Block and Inception Module for Qualitative Image
Year: 2024
Type: article
Abstract: 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.
Authors: Yeeun Kim, Ayoung Nam, Dana Yang
Institution: Korean Bible University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4404779976