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.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2018
- DOI:
- 10.48550/arXiv.1811.04761
- arXiv:
- arXiv:1811.04761
- Bibcode:
- 2018arXiv181104761L
- Keywords:
-
- Electrical Engineering and Systems Science - Image and Video Processing
- E-Print:
- Accepted by ICIP 19. Corresponding author: Hanrong Ye