Single Image Raindrop Removal Using a Non-local Operator and Feature Maps in the Frequency Domain

Shinya Ezumi, Masaaki Ikehara

Research output: Contribution to journalArticlepeer-review


Taking a photo on a rainy day may result in a photo with raindrops. Images containing raindrops have a significant impact on the visual impression and accuracy when applied to image recognition systems. Thus, an automatic high-quality raindrop removal method is desired for outdoor image processing systems as well as for acquiring good-looking images. Several existing methods have been proposed to tackle this problem, but they often fail to keep global consistency and generate unnatural patterns. In this paper, we tackle this problem by introducing a non-local operator. The non-local operator combines features in distant locations with matrix multiplication and enables consistency in distant locations. In addition, high-frequency components such as edges are more affected in images with raindrops. Inspired by the nature that high-frequency components can be separated from other components in the frequency domain, we also propose to process feature maps in the frequency domain, which are obtained by the fast Fourier transform operation and processed by several convolution layers. Experimental results show that our method effectively removes raindrops and achieves state-of-the-art performance.

Original languageEnglish
Pages (from-to)1
Number of pages1
JournalIEEE Access
Publication statusAccepted/In press - 2022


  • Convolutional neural networks
  • Decoding
  • Deep learning
  • Fast Fourier transforms
  • Fast Fourier transforms
  • Feature extraction
  • Frequency-domain analysis
  • Image edge detection
  • Image processing
  • Image restoration
  • Image restoration

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Single Image Raindrop Removal Using a Non-local Operator and Feature Maps in the Frequency Domain'. Together they form a unique fingerprint.

Cite this