Self-Refining Deep Symmetry Enhanced Network for Rain Removal

Abstract

Rain removal aims to remove the rain streaks on rain images. The state-of-the-art methods are mostly based on Convolutional Neural Network~(CNN). However, as CNN is not equivariant to object rotation, these methods are unsuitable for dealing with the tilted rain streaks. To tackle this problem, we propose Deep Symmetry Enhanced Network~(DSEN) that is able to explicitly extract the rotation equivariant features from rain images. In addition, we design a self-refining mechanism to remove the accumulated rain streaks in a coarse-to-fine manner. This mechanism reuses DSEN with a novel information link which passes the gradient flow to the higher stages. Extensive experiments on both synthetic and real-world rain images show that our self-refining DSEN yields the top performance.

Comment: Accepted by ICIP 19. Corresponding author: Hanrong Ye

Original document

The different versions of the original document can be found in:

• http://arxiv.org/abs/1811.04761

• https://ink.library.smu.edu.sg/sis_research/4449 under the license cc-by-nc-nd

• http://xplorestaging.ieee.org/ielx7/8791230/8799366/08803265.pdf?arnumber=8803265,

http://dx.doi.org/10.1109/icip.2019.8803265

• https://dblp.uni-trier.de/db/conf/icip/icip2019.html#0008YLSLS19,

https://ink.library.smu.edu.sg/sis_research/4449,

https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=5452&context=sis_research,

https://academic.microsoft.com/#/detail/2970543065