Kong Dechuan, Zhang Yandi, Zhao Xiaohu, Wang Yanyan, Wang Yanqiang
School of Artificial Intelligence, Henan Institute of Science and Technology, Xinxiang 453003, China.
National and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou 221116, China.
Sensors (Basel). 2025 Sep 2;25(17):5439. doi: 10.3390/s25175439.
Underwater imaging is affected by spatially varying blur caused by water flow turbulence, light scattering, and camera motion, resulting in severe visual quality loss and diminished performance in downstream vision tasks. Although numerous underwater image enhancement methods have been proposed, the issue of addressing non-uniform blur under realistic underwater conditions remains largely underexplored. To bridge this gap, we propose PMSPNet, a Progressive Multi-Scale Perception Network, designed to handle underwater non-uniform blur. The network integrates a Hybrid Interaction Attention Module to enable precise modeling of feature ambiguity directions and regional disparities. In addition, a Progressive Motion-Aware Perception Branch is employed to capture spatial orientation variations in blurred regions, progressively refining the localization of blur-related features. A Progressive Feature Feedback Block is incorporated to enhance reconstruction quality by leveraging iterative feature feedback across scales. To facilitate robust evaluation, we construct the Non-uniform Underwater Blur Benchmark, which comprises diverse real-world blur patterns. Extensive experiments on multiple real-world underwater datasets demonstrate that PMSPNet consistently surpasses state-of-the-art methods, achieving on average 25.51 dB PSNR and an inference speed of 0.01 s, which provides high-quality visual perception and downstream application input from underwater sensors for underwater robots, marine ecological monitoring, and inspection tasks.
水下成像会受到水流湍流、光散射和相机运动所引起的空间变化模糊的影响，导致视觉质量严重下降，以及下游视觉任务的性能降低。尽管已经提出了许多水下图像增强方法，但在实际水下条件下解决非均匀模糊的问题在很大程度上仍未得到充分探索。为了弥补这一差距，我们提出了PMSPNet，一种渐进式多尺度感知网络，旨在处理水下非均匀模糊。该网络集成了一个混合交互注意力模块，以实现对特征模糊方向和区域差异的精确建模。此外，采用了一个渐进式运动感知感知分支来捕捉模糊区域中的空间方向变化，逐步细化与模糊相关特征的定位。引入了一个渐进式特征反馈块，通过跨尺度利用迭代特征反馈来提高重建质量。为了便于进行稳健的评估，我们构建了非均匀水下模糊基准，它包含各种真实世界的模糊模式。在多个真实世界水下数据集上进行的大量实验表明，PMSPNet始终超越现有方法，平均实现25.51 dB的峰值信噪比和0.01秒的推理速度，为水下机器人、海洋生态监测和检测任务提供了来自水下传感器的高质量视觉感知和下游应用输入。
