Boosting Image Quality with Generative Adversarial Networks in the context of Super-Resolution

DOI

10.2991/978-94-6239-727-9_18How to use a DOI?

Keywords

Image Super-Resolution; Generative Adversarial Networks; SRGAN; Deep Learning; High-Resolution Image Reconstruction; Computer Vision; Perceptual Loss; Neural Networks

Abstract

Image super-resolution (SR) plays a vital role in enhancing low-resolution data across applications such as remote sensing, medical imaging, and video processing. Traditional interpolation and statistical methods often fail to recover fine details, whereas deep learning approaches, particularly GAN-based models like SRGAN and ESRGAN, have significantly improved reconstruction quality. However, these models face challenges including unstable training, high computational cost, and perceptual–distortion trade-offs. This paper presents a hybrid super-resolution framework that integrates GAN architecture with transformer-based attention and self-supervised learning. The proposed model captures long-range dependencies, reduces reliance on labeled datasets, and introduces adaptive loss balancing to improve both visual quality and reconstruction accuracy. Experimental comparisons demonstrate improved PSNR, SSIM, and perceptual quality over existing methods. The approach offers better stability and generalization, making it suitable for diverse real-world imaging applications while addressing key limitations of current GAN-based SR techniques.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Arunesh Pratap Singh
AU  - Rasna Nikunjkumar Patel
AU  - Ankita Verma
AU  - Sanjay Pagare
AU  - Alok Singh Kushwaha
PY  - 2026
DA  - 2026/07/22
TI  - Boosting Image Quality with Generative Adversarial Networks in the context of Super-Resolution
BT  - Proceedings of the International Conference on Sustainable Micro-Nano Materials & Innovative Technology (ICSUMMIT 2026)
PB  - Atlantis Press
SP  - 235
EP  - 253
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-727-9_18
DO  - 10.2991/978-94-6239-727-9_18
ID  - Singh2026
ER  -