Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal

Fu, Xueyang; Huang, Jia‐Bin; Ding, Xinghao; Liao, Yinghao; Paisley, John

doi:10.1109/tip.2017.2691802

articleIEEE Transactions on Image ProcessingApr 6, 2017GREEN OA

Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal

XFXueyang Fu JHJia‐Bin Huang XDXinghao Ding YLYinghao Liao JPJohn Paisley

Xiamen University · Columbia University

PubMed

Indexed inarxivcrossrefpubmed

Abstract

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…

Citation impact

954

total citations

FWCI: 28.00
Percentile: 100%
References: 42

Citations per year

Authors

5

Topics & keywords

Topics

Keywords

Computer science
Convolutional neural network
Artificial intelligence
Image (mathematics)
Network architecture
Domain (mathematical analysis)
Deep learning
Image processing

UN Sustainable Development Goals

Sustainable cities and communities

No related works found for this paper.