Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176026,
        author = {Yash Chavan and Saili Sable and Ayush Rai and Atharv Mahajan and Sarthak Bharambe},
        title = {Image Quality Enhancement using Real-ESRGAN: A Comprehensive Review of Datasets and Approaches},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {6436-6441},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176026},
        abstract = {Rapid developments in image restoration techniques have helped to reduce noise, compression artifacts, and low-resolution images challenges. Real-ESRGAN extends ESRGAN on practical applications in real-world practice by incorporating a high-order degradation model, synthetic training pipelines, and advanced architectures of discriminator. This article reviews its methodologies, provides comparisons of its performance using state-of-the-art techniques, and surveys recent related literature. Its applications, comparative strengths, and future directions are highlighted to bridge existing gaps in the field.},
        keywords = {Image Enhancement, Super-Resolution, Real- ESRGAN, ESRGAN, JPEG Artifacts, REAL-ESRGAN, PSNR, SSIM.},
        month = {April},
        }