Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network

He Zhang, Vishal M. Patel; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 695-704

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 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2018_CVPR,
author = {Zhang, He and Patel, Vishal M.},
title = {Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}