In recent years, removing rain streaks from a single image has been a significant issue for outdoor vision tasks. In this paper, we propose a novel recursive residual atrous spatial pyramid pooling network to directly recover the clear image from rain image. Specifically, we adopt residual atrous spatial pyramid pooling (ResASPP) module which is constructed by alternately cascading a ResASPP block with a residual block to exploit multi-scale rain information. Besides, taking the dependencies of deep features across stages into consideration, a recurrent layer is introduced into ResASPP to model multi-stage processing procedure from coarse to fine. For each stage in our recursive network we concatenate the stage-wise output with the original rainy image and then feed them into the next stage. Furthermore, the negative SSIM loss and perceptual loss are employed to train the proposed network. Extensive experiments on both synthetic and real-world rainy datasets demonstrate that the proposed method outperforms the state-of-the-art deraining methods.

近年来，从单个图像中去除雨水条纹一直是户外视觉任务的一个重要问题。在本文中，我们提出了一种新颖的递归残差空洞空间金字塔池化网络，以直接从雨图像中恢复清晰图像。具体来说，我们采用残差多孔空间金字塔池化（ResASPP）模块，该模块通过将 ResASPP 块与残差块交替级联而构建，以利用多尺度降雨信息。此外，考虑到跨阶段深度特征的依赖关系，在 ResASPP 中引入了一个循环层来模拟从粗到细的多阶段处理过程。对于递归网络中的每个阶段，我们将阶段输出与原始雨天图像连接起来，然后将它们输入到下一个阶段。此外，使用负 SSIM 损失和感知损失来训练所提出的网络。对合成和现实世界下雨数据集的大量实验表明，所提出的方法优于最先进的去雨方法。