MIMAR-Net: Multiscale Inception-based Manhattan Attention Residual Network and its application to underwater image super-resolution

Electronics
By: , and 

Links

Abstract

In recent years, Single-Image Super-Resolution (SISR) has gained significant attention in the geoscience and remote sensing community for its potential to improve the resolution of low-quality underwater imagery. This paper introduces MIMAR-Net (Multiscale Inception-based Manhattan Attention Residual Network), a new deep learning architecture designed to increase the spatial resolution of input color images. MIMAR-Net integrates a multiscale inception module, cascaded residue learning, and advanced attention mechanisms, such as the MaSA layer, to capture both local and global contextual information effectively. By utilizing multiscale processing and advanced attention strategies, MIMAR-Net allows us to handle the complexities of underwater environments with precision and robustness. We evaluate the model on three popular underwater image datasets, namely UFO-120, USR-248, and EUVP, and perform extensive comparisons against state-of-the-art methods. Experimental results demonstrate that MIMAR-Net consistently outperforms existing approaches, achieving superior qualitative and quantitative improvements in image quality, making it a reliable solution for underwater image enhancement in various challenging scenarios.

Publication type Article
Publication Subtype Journal Article
Title MIMAR-Net: Multiscale Inception-based Manhattan Attention Residual Network and its application to underwater image super-resolution
Series title Electronics
DOI 10.3390/electronics14224544
Volume 14
Issue 22
Publication Date November 20, 2025
Year Published 2025
Language English
Publisher MDPI
Contributing office(s) Great Lakes Science Center
Description 4544, 24 p.
Additional publication details