基于雨雾分离处理和多尺度网络的图像去雨方法

雨带来的雨条纹和雨雾会降低户外拍摄图像的质量，为了去除雨雾对图像的影响，提出了一种基于雨雾分离处理和多尺度卷积神经网络的图像去雨方法。首先利用导向滤波将雨线和图像细节信息提取到高频层，雨雾和背景信息则分离到低频层；然后构建多尺度卷积神经网络来去除高频层中的雨线，网络中融入多个稠密连接模块以提升特征提取的准确性；其次构建多层特征融合的轻量级去雾网络来去除低频层中的雨雾，采用参数一体化结构避免了估计多个大气散射模型参数导致的次优解；最后再结合处理后的高低频结果还原出清晰图像。在多个合成的雨雾数据集以及真实自然场景图像上进行测试，定性和定量结果表明，提出的方法在去除雨雾影响的同时较好地保留了色彩信息，和近年的算法相比，图像结构相似性约提升了0.02~0.08，图像峰值信噪比约提升了0.2~3.5 dB。

Image rain removal method based on rain and fog separation processing and multiscale network

Rain streaks and fog brought by rain can degrade the quality of images taken outdoors. In order to remove the influence of rain and fog on images, this paper proposed an image derain method based on rain and fog separation processing and multi-scale convolutional neural network. Firstly, it extracted the rain lines and image details to the high frequency layer using guided filtering, while separated the fog and background information to the low frequency layer. Then it constructed a multi-scale convolutional neural network to remove the rain lines in the high frequency layer, and incorporated multiple dense connection modules into the network to improve the accuracy of feature extraction. Secondly, it constructed a lightweight defogging network with multi-layer feature fusion to remove the fog in the low frequency layer, and used the parameter integration structure to avoid estimation of multiple atmospheric scattering model parameters resulting in sub-optimal solutions. Finally, it combined the processed high and low frequency results to restore a clear image. Tested on several synthetic rain and fog datasets as well as on real natural scene images, the qualitative and quantitative results show that the method in this paper removes rain and fog while retaining color information well, and improves the image structure similarity by 0.02 to 0.08 and the image peak signal-to-noise ratio by 0.2 to 3.5 dB compared to recent algorithms.