Clearing the Skies: A deep network architecture for single-image rain removal

7 Sep 2016  ·  Xueyang Fu, Jia-Bin Huang, Xinghao Ding, Yinghao Liao, John Paisley ·

We introduce a deep network architecture called DerainNet for removing rain streaks from an image. Based on the deep convolutional neural network (CNN), we directly learn the mapping relationship between rainy and clean image detail layers from data. Because we do not possess the ground truth corresponding to real-world rainy images, we synthesize images with rain for training. In contrast to other common strategies that increase depth or breadth of the network, we use image processing domain knowledge to modify the objective function and improve deraining with a modestly-sized CNN. Specifically, we train our DerainNet on the detail (high-pass) layer rather than in the image domain. Though DerainNet is trained on synthetic data, we find that the learned network translates very effectively to real-world images for testing. Moreover, we augment the CNN framework with image enhancement to improve the visual results. Compared with state-of-the-art single image de-raining methods, our method has improved rain removal and much faster computation time after network training.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Single Image Deraining Rain100H DerainNet PSNR 14.92 # 10
SSIM 0.592 # 9
Single Image Deraining Rain100L DerainNet PSNR 27.03 # 9
SSIM 0.884 # 9
Single Image Deraining Test100 DerainNet PSNR 22.77 # 9
SSIM 0.810 # 9
Single Image Deraining Test1200 DerainNet PSNR 23.38 # 10
SSIM 0.835 # 9
Single Image Deraining Test2800 DerainNet PSNR 24.31 # 10
SSIM 0.861 # 9


No methods listed for this paper. Add relevant methods here