부산대학교 도서관

Underwater images are important in a range of image-driven applications, such as marine biology and underwater surveillance. However, underwater imaging is subject to several factors that can severely degrade image quality, i.e., light absorption and scattering within the water column. An effective underwater image quality assessment (UIQA) metric is therefore needed to accurately quantify image quality, subsequently facilitating the follow-up of underwater vision tasks. In this article, we propose a novel feature-interaction-based UIQA framework, namely, SISC, which addresses the challenges of training data scarcity and complex underwater degradation conditions. A feature refinement module is dedicatedly designed based on self-attention to implement local and nonlocal cross-spatial feature interactions. In addition, we enhance the refined features in a cross-scale fashion using upsampling and downsampling strategies based on cross-attention. With the two stages of feature refinement and feature enhancement, the proposed SISC achieves data-efficient learning and superior performance compared to existing state-of-the-art UIQA and natural IQA (images captured in air) methods, indicating its effectiveness in extracting quality-aware features from underwater images.