Single-image rain removal using residual deep learning

Takuro Matsui, Takanori Fujisawa, Takuro Yamaguchi, Masaaki Ikehara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)


Most outdoor vision systems can be influenced by rainy weather conditions. In this paper, we address a rain removal problem from a single image. Some existing de-raining methods suffer from hue change due to neglect of the information in low frequency layer. Others fail in assuming enough rainy image models. To solve them, we propose a residual deep network architecture called ResDerainNet. Based on the deep convolutional neural network (CNN), we learn the mapping relationship between rainy and residual images from data. Furthermore, for training, we synthesize rainy images considering various rain models. Specifically, we mainly focus on the composite models as well as orientations and scales of rain streaks. The experiments demonstrate that our proposed model is applicable to a variety of images. Compared with state-of-the-art methods, our proposed method achieves better results on both synthetic and real-world images.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781479970612
Publication statusPublished - 2018 Aug 29
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 2018 Oct 72018 Oct 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Conference25th IEEE International Conference on Image Processing, ICIP 2018


  • Batch normalization
  • Convolutional neural networks
  • Deep learning
  • Rain removal
  • Residual learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'Single-image rain removal using residual deep learning'. Together they form a unique fingerprint.

Cite this