Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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

He Zhang, Vishal M. Patel• 2018

Related benchmarks

TaskDatasetResultRank
Image DerainingRain100L (test)
PSNR25.23
161
Image DerainingRain100L
PSNR25.23
152
DerainingRain100L (test)
PSNR23.79
90
Image DerainingTest100 (test)
PSNR22.56
53
Image DerainingRain100H
PSNR17.35
52
DerainingRain100H (test)
PSNR17.35
50
Image DerainingRain100H (test)
PSNR17.35
40
Image Deraining2800 (test)
PSNR28.13
34
Image Deraining1200 (test)
PSNR29.65
28
Image DerainingAverage across Deraining Datasets (test)
PSNR24.58
26
Showing 10 of 35 rows

Other info

Code

Follow for update