Density-Aware Single Image De-raining Using a Multi-stream Dense Network
Density-Aware Single Image De-raining Using a Multi-stream Dense Network
复制标题
DOI：
10.1109/cvpr.2018.00079
复制
发表时间：
2018-02
期刊：
影响因子：
--
通讯作者：
He Zhang;Vishal M. Patel
中科院分区：
文献类型：
--
作者：
He Zhang;Vishal M. Patel
由于图像中存在不均匀的雨密度，单幅图像的雨条纹去除是一个极具挑战性的问题。我们提出了一种新的基于密度感知的多流密集连接卷积神经网络算法，称为DID-MDN，用于联合雨密度估计和去雨。该方法使网络自身能够自动确定雨密度信息，然后在估计的雨密度标签的引导下有效地去除相应的雨条。为了更好地表征不同尺度和形状的雨条，提出了一种多流密集连接的去雨网络，有效地利用了不同尺度的特征。此外，还创建了一个包含带有雨密度标签的图像的新数据集，并用于训练所提出的密度感知网络。在合成数据集和真实数据集上进行的大量实验表明，所提出的方法比目前最先进的方法取得了显着改进。此外，还进行了烧蚀研究，以证明在所提出的方法中不同模块所获得的改进。代码可以从https://github.com/hezhangsprinter/DID-MDN下载
Single image rain streak removal is an extremely challenging problem due to the presence of non-uniform rain densities in images. We present a novel density-aware multi-stream densely connected convolutional neural network-based algorithm, called DID-MDN, for joint rain density estimation and de-raining. The proposed method enables the network itself to automatically determine the rain-density information and then efficiently remove the corresponding rain-streaks guided by the estimated rain-density label. To better characterize rain-streaks with different scales and shapes, a multi-stream densely connected de-raining network is proposed which efficiently leverages features from different scales. Furthermore, a new dataset containing images with rain-density labels is created and used to train the proposed density-aware network. Extensive experiments on synthetic and real datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. In addition, an ablation study is performed to demonstrate the improvements obtained by different modules in the proposed method. The code can be downloaded at https://github.com/hezhangsprinter/DID-MDN