Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

9-2019

Abstract

Rain removal aims to remove the rain streaks on rain images. Traditional methods based on convolutional neural network (CNN) have achieved impressive results. However, these methods are under-performed when dealing with tilted rain streaks, because CNN is not equivariant to object rotations. To tackle this problem, we propose the Deep Symmetry Enhanced Network (DSEN) that explicitly extracts and learns from rotation-equivariant features from rain images. In addition, we design a self-refining strategy to remove rain streaks in a coarse-to-fine manner. The key idea is to reuse DSEN with an information link which passes the gradient flow to the finer stage. Extensive experimental results on both synthetic and real-world rain images show that our method of self-refined DSEN yields top performance for rain removal.

Keywords

Image Restoration, Rotation Equivariance, CNN

Discipline

Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

2019 IEEE International Conference on Image Processing (ICIP): Taipei, September 22-25: Proceedings

First Page

2786

Last Page

2790

ISBN

9781538662496

Identifier

10.1109/ICIP.2019.8803265

Publisher

IEEE

City or Country

Piscataway, NJ

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/ICIP.2019.8803265

Share

COinS