Copyright © 2026 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{183047,
        author = {Samyuktha Anand and Ayush Gupta and Gajraj Singh},
        title = {Underwater Image Super-Resolution using GANs},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {16-21},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183047},
        abstract = {Underwater images tend to suffer from poor resolution, color distortion and reduced visibility caused by light scattering and absorption in the underwater environment. This quality degradation significantly affects subsequent downstream tasks like object detection, marine life monitoring and autonomous underwater navigation. Here, we introduce a novel deep learning-based underwater image super-resolution framework based on Generative Adversarial Networks (GANs). Our approach combines a modified USRNet backbone with GAN-based refinement to recover high-frequency details and perceptual quality while maintaining structural fidelity. We train the model on a composite dataset of UFO-120, UIEB and EUVP to increase robustness in diverse underwater environments. Quantitative outcomes show significant gains in PSNR and SSIM over the state-of-the-art, while qualitative assessment verifies higher visual clarity. The suggested method provides a promising avenue for improving underwater images in practical applications.},
        keywords = {Underwater image enhancement, super-resolution, generative adversarial networks, deep learning, image restoration, USRNet.},
        month = {July},
        }