Density-aware Single Image De-raining using a Multi-stream Dense Network

CVPR 2018  ·  He Zhang, Vishal M. Patel ·

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. Code can be found at: https://github.com/hezhangsprinter

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Single Image Deraining Rain100H DIDMDN SSIM 0.524 # 14
Single Image Deraining Rain100L DIDMDN SSIM 0.741 # 17
Single Image Deraining RainCityscapes DID-MDN PSNR 28.43 # 6
SSIM 0.9349 # 6
Single Image Deraining Test100 DIDMDN SSIM 0.818 # 10
Single Image Deraining Test1200 DIDMDN SSIM 0.901 # 10
Single Image Deraining Test2800 DIDMDN PSNR 28.13 # 9
SSIM 0.867 # 9

Methods


No methods listed for this paper. Add relevant methods here