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）对高层次的水下视觉任务至关重要。尽管近年来基于学习的UIE方法取得了显著成就，但它们仍难以一致性地处理各种水下环境，这可能由以下原因导致：1）UIE中使用的简化大气图像形成模型可能产生严重误差；2）仅使用合成图像训练的网络可能难以较好地泛化到真实水下图像。本研究首次提出了一种名为\textit{SyreaNet}的UIE框架，该框架在修订的水下图像形成模型和新型领域自适应（DA）策略的指导下，融合了合成数据与真实数据。首先，基于修订模型提出了一个水下图像合成模块。其次，设计了一个物理引导的解耦网络，通过结合合成与真实水下图像来预测清晰图像。通过充分交换领域知识，缩小了领域内和领域间的差异。大量实验定性和定量地证明了我们框架相较于其他基于学习的最先进（SOTA）UIE方法的优越性。代码和数据集已公开于https://github.com/RockWenJJ/SyreaNet.git。