Multi-scale cascaded attention network for underwater image enhancement

The complexity of underwater environments combined with light attenuation and scattering in water often leads to quality degradation in underwater images, including color distortion and blurred details. To eliminate obstacles in underwater imaging, we propose an underwater image enhancement method based on a cascaded attention network called MSCA-Net. Specifically, this method designs an attention-guided module that connects channel and pixel attention in both serial and parallel ways to simultaneously achieve channel feature refinement and feature representation enhancement. Afterward, we propose a multi-scale feature integration module to capture information and details at different scales within the image. Meanwhile, residual connections are introduced to assist in deep feature learning via acquiring more detailed information from shallow features. We conducted extensive experiments on various underwater datasets, and the results demonstrate that our method still holds an advantage when compared to the latest underwater image enhancement methods.