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{205227,
        author = {Prasad M. Bhakare and Ishan S. Kulkarni and Kapirath Raina and Aditya P. Bhole and Swati N. Firame},
        title = {Ocean-water Imagery Enhancement using CNN and GAN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {6328-6335},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205227},
        abstract = {Poor underwater imagery, due to limited illumination, scattering of light by water particles, and distorted colour representation, often detracts from its usefulness in practical applications for marine research, defence operations, and environmental monitoring. To overcome such challenges, we designed a novel approach, which integrates CNNs with GANs for improving the quality of an image. Our model was trained on the EUVP dataset and proved very effective in restoring clarity, recovering real colours, and eliminating noisy artifacts. Experimental results demonstrate significant improvements that result in visually better-quality images with great similarity to real-world scenarios. It opens up the possibility to perform oceanographic analysis more accurately and to explore and exploit marine resources in an overall better and more sustainable way.},
        keywords = {Underwater Photo Fixing, Smart Computer Model, CNN, GAN, Mixed Model, Deep Learning, Photo Change, Computer Seeing, EUVP Photo Set, Seeing Better, Smart Machine.},
        month = {June},
        }