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

Authors:

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 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 the state-of-the-art single image de-raining methods, our method has improved rain removal and much faster computation time after network training.
Funding Information
  • National Natural Science Foundation of China (61571382, 81671766, 61571005, 81671674, U1605252, 61671309, 81301278)
  • Guangdong Natural Science Foundation (2015A030313007)
  • Fundamental Research Funds for the Central Universities (20720160075, 20720150169)
  • Natural Science Foundation of Fujian Province of China (2017J01126)
  • CCF-Tencent research fund
  • China Scholarship Council ([2016]3100)

This publication has 27 references indexed in Scilit: