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{208085,
        author = {Sai Keerthana Sandhiri and Buddi Reethika Chovudary and Sama Rohith Reddy},
        title = {Underwater Image Hyper-Resolution Using MLDRG},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {4},
        pages = {259-263},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208085},
        abstract = {Turbidity, light absorption, sediment, and other environmental factors greatly hinder imaging in the underwater setting and degrade image quality. Standard procedures such as white balance and histogram equalization do not improve the visuals. In this work, we propose a deep learning framework for hyper-resolution underwater images and design a Multi-Level Degradation Restoration Generator (MLDRG) framework specifically to denoise and correct color distortion for underwater imagery. To improve the texture and resolution further, the model also incorporates a High-Frequency Learning Module (HFLM). The proposed model also demonstrates good transferability after being trained on a global underwater image dataset. The evaluation of the model with the PSNR and SSIM metrics, along with the modified Clarity Index, exhibited the advanced performance of the proposed technique against traditional techniques in color reproduction, resolution boost, structure retention, and other aspects. The work demonstrates further development of underwater imaging systems for possible use in marine studies, navigation robotics, and submerged vehicle systems. The primary focus of the research is writing advanced techniques for the Global Maritime Systems Dataset Underwater images, applying deep learning, hyper-resolution and image enhancement using MLDRG and HFLM.},
        keywords = {Underwater Imaging, Deep Learning, Hyper-Resolution, MLDRG, HFLM, Image Restoration, PSNR, SSIM, Global Marine Dataset, Image Enhancement.},
        month = {September},
        }