Underwater image enhancement (UIE) is vital for high-level vision-related underwater tasks. Although learning-based UIE methods have made remarkable achievements in recent years, it's still challenging for them to consistently deal with various underwater conditions, which could be caused by: 1) the use of the simplified atmospheric image formation model in UIE may result in severe errors; 2) the network trained solely with synthetic images might have difficulty in generalizing well to real underwater images. In this work, we, for the first time, propose a framework \textit{SyreaNet} for UIE that integrates both synthetic and real data under the guidance of the revised underwater image formation model and novel domain adaptation (DA) strategies. First, an underwater image synthesis module based on the revised model is proposed. Then, a physically guided disentangled network is designed to predict the clear images by combining both synthetic and real underwater images. The intra- and inter-domain gaps are abridged by fully exchanging the domain knowledge. Extensive experiments demonstrate the superiority of our framework over other state-of-the-art (SOTA) learning-based UIE methods qualitatively and quantitatively. The code and dataset are publicly available at https://github.com/RockWenJJ/SyreaNet.git.
翻译:水下图像增强(UIE)对于水下高层次与视觉有关的水下任务至关重要。尽管基于学习的UIE方法近年来取得了显著成就,但对于它们来说,持续处理各种水下条件仍具有挑战性,原因可能是:(1) 在UIE中使用简化的大气图像形成模型可能导致严重错误;(2) 仅以合成图像培训的网络可能难以将合成图像推广到真正的水下图像。在这项工作中,我们首次为UIE提议一个框架\ textit{SyreaNet},在经修订的水下图像形成模型和新版域适应战略的指导下,将合成数据和真实数据结合起来。首先,根据经修订的模型提出水下图像合成模型合成模块。然后,设计一个物理引导分解的网络,通过合成图像和真实水下图像相结合来预测清晰的图像。通过充分交换域知识,内部和内部差距是缩小的。广泛的实验表明我们的框架优于其他状态-艺术(SOITA)学习的UIE/Weqram/Q.