Mamba-convolution hybrid network for underwater image enhancement

• Published in: Scientific reports Vol. 15; no. 1; p. 31975
• Main Authors: Chen, Hailan, Wang, Yijian, Wu, Lihua, Hu, Hao, Yan, Jiaquan, Xu, Haiping, Lei, Guowei
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 30.08.2025; Nature Publishing Group
• Subjects: 639/166; 639/624; Convolution; Design; Ecological monitoring; Humanities and Social Sciences; Illumination; Marine environment; Methods; multidisciplinary; Neural networks; Science; Science (multidisciplinary); Underwater; Underwater robots; Underwater image enhancement; disentanglement strategy; multiscale feature fusion; underwater optical imaging

Underwater imagery frequently exhibits low clarity and is subject to significant color distortion as a result of the inherent conditions of the marine environment and variations in illumination. Such degradation in image quality fundamentally undermines the efficacy of marine ecological monitoring a...