Single Image Deraining using a Recurrent Multi-scale Aggregation and Enhancement Network
Single Image Deraining using a Recurrent Multi-scale Aggregation and Enhancement Network
复制标题
DOI：
10.1109/icme.2019.00239
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Youzhao Yang;Hong Lu
中科院分区：
文献类型：
--
作者：
Youzhao Yang;Hong Lu
由于图像中雨的形状、方向和密度的不均匀性，单幅图像的反求是一个不适定的逆问题。本文提出了一种新的渐进式单图像去噪方法--递归多尺度聚合增强网络（ReMAEN）。与以往的方法不同，ReMAEN包含一个对称的结构，其中使用共享信道注意力的递归块来协同选择有用的信息，并逐步消除雨条纹。在ReMAEN中，多尺度聚合和增强块（MAEB）被构造用于检测多尺度雨细节。此外，为了更好地利用雨天图像中的雨水细节，ReMAEN实现了从低级别到高级别的对称跳跃连接。在合成数据集和真实数据集上的大量实验表明，我们的方法大大优于最先进的方法。源代码可在https://github.com/nnUyi/ReMAEN上获得。
Single image deraining is an ill-posed inverse problem due to the presence of non-uniform rain shapes, directions, and densities in images. In this paper, we propose a novel progressive single image deraining method named Recurrent Multi-scale Aggregation and Enhancement Network (ReMAEN). Differing from previous methods, ReMAEN contains a symmetric structure where recurrent blocks with shared channel attention are applied to select useful information collaboratively and remove rain streaks stage by stage. In ReMAEN, a Multi-scale Aggregation and Enhancement Block (MAEB) is constructed to detect multi-scale rain details. Moreover, to better leverage the rain details from rainy images, ReMAEN enables a symmetric skipping connection from low level to high level. Extensive experiments on synthetic and real-world datasets demonstrate that our method outperforms the state-of-the-art methods tremendously. The source code is available at https://github.com/nnUyi/ReMAEN.