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.
@article{arxiv.1811.04761,
title = {Self-Refining Deep Symmetry Enhanced Network for Rain Removal},
author = {Hong Liu and Hanrong Ye and Xia Li and Wei Shi and Mengyuan Liu and Qianru Sun},
journal= {arXiv preprint arXiv:1811.04761},
year = {2020}
}
Comments
Accepted by ICIP 19. Corresponding author: Hanrong Ye