AUIQE: Attention-Based Underwater Image Quality Evaluator

Baochao Zhang, Chenghao Zhou, Runze Hu, Jingchao Cao, Yutao Liu

Abstract: Underwater image quality assessment (UIQA) is critical to many underwater application scenarios, including marine biology research, marine resource development, underwater exploration, and more. Due to the different attenuation rates of light at different wavelengths and the effects of the absorption and scattering of light by suspended particles in the water, there are many types of distortion in the acquired underwater images. Most underwater images often show color casts, reduced contrast, low brightness, blurred object edges, local texture distortion, etc. degradation phenomena compared to natural images. This renders many of the image quality assessment (IQA) methods designed for natural images inapplicable to underwater images. Currently, there is a lack of UIQA methods that are accurate and efficient. In this paper, we proposed an Attention-Based Underwater Image Quality Evaluator (AUIQE), a novel end-to-end IQA approach suitable for UIQA tasks. Specifically, we introduced channel and spatial dual attention mechanisms on the basis of the distortion characteristics of underwater images to make the network focus on some channels and spatial regions that are relevant to image quality. A large number of experiments were designed and carried out on an underwater image quality assessment dataset, and the experimental results indicate that the prediction performance of AUIQE outperforms some of the latest IQA and UIQA methods. The code of AUIQE will be available at https://github.com/ibaochao/AUIQE.