Abstract
Recently, single-image rain removal has attracted sustained attention. In this paper, we utilize a simple shape prior, the fact that the rain streaks often appear in an elongated elliptical shape, in a particular way for single image de-raining. With this prior, the patches of the rain layer are forced to have a high correlation with our synthetic ellipse matrix. Then, the rain layer is refined during each layer decomposition process with the correlation constraints. The experiments show that the proposed method outperforms the existing single image de-raining methods on both real and synthetic data. Moreover, our approach runs much faster than the other state-of-the-art de-raining methods.
Funding Information
  • National Key R&D Program of China (2016YFB0200602, 2017YFB1002701)
  • National Natural Science Foundation of China (61702112, 61502109, 61672502, 61772142)
  • China Postdoctoral Science Foundation (2017M612614)
  • Science and technology project of Guangdong Province (2015B010128014, 2017B010110015, 2017B010110007)
  • Natural Science Foundation of Guangdong Province (2016A030310342)
  • Opening Project of the Guangdong Province Key Laboratory of Computational Science, Sun Yat-sen University (2018012)
  • Science and Technology Program of Guangzhou (201707010147)
  • Pearl River S&T Nova Program of Guangzhou (201806010059)

This publication has 30 references indexed in Scilit: