Abstract
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 densityaware 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 raindensity 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 signifi-
cant 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