Hu Haofeng, Han Yilin, Li Xiaobo, Jiang Liubing, Che Li, Liu Tiegen, Zhai Jingsheng
Opt Express. 2022 Jun 20;30(13):22512-22522. doi: 10.1364/OE.461074.
Utilizing the polarization analysis in underwater imaging can effectively suppress the scattered light and help to restore target signals in turbid water. Neural network-based solutions can also boost the performance of polarimetric underwater imaging, while most of the existing networks are pure data driven which suffer from ignoring the physical mode. In this paper, we proposed an effective solution that informed the polarimetric physical model and constrains into the well-designed deep neural network. Especially compared with the conventional underwater imaging model, we mathematically transformed the two polarization-dependent parameters to a single parameter, making it easier for the network to converge to a better level. In addition, a polarization perceptual loss is designed and applied to the network to make full use of polarization information on the feature level rather than on the pixel level. Accordingly, the network was able to learn the polarization modulated parameter and to obtain clear de-scattered images. The experimental results verified that the combination of polarization model and neural network was beneficial to improve the image quality and outperformed other existing methods, even in a high turbidity condition.
利用水下成像中的偏振分析可以有效抑制散射光，并有助于在浑浊水中恢复目标信号。基于神经网络的解决方案也可以提高偏振水下成像的性能，而现有的大多数网络都是纯数据驱动的，存在忽视物理模型的问题。在本文中，我们提出了一种有效的解决方案，即将偏振物理模型和约束条件引入精心设计的深度神经网络中。特别是与传统的水下成像模型相比，我们将两个与偏振相关的参数进行数学变换，使其成为一个单一参数，从而使网络更容易收敛到更好的水平。此外，还设计了一种偏振感知损失并应用于网络，以便在特征层面而非像素层面充分利用偏振信息。相应地，该网络能够学习偏振调制参数并获得清晰的去散射图像。实验结果验证了偏振模型与神经网络的结合有利于提高图像质量，并且即使在高浑浊度条件下也优于其他现有方法。
