AI RESEARCH

Hero-Mamba: Mamba-based Dual Domain Learning for Underwater Image Enhancement

arXiv CS.CV

ArXi:2604.16266v1 Announce Type: new Underwater images often suffer from severe degradation, such as color distortion, low contrast, and blurred details, due to light absorption and scattering in water. While learning-based methods like CNNs and Transformers have shown promise, they face critical limitations: CNNs struggle to model the long-range dependencies needed for non-uniform degradation, and Transformers incur quadratic computational complexity, making them inefficient for high-resolution images.