Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network

By Ruoteng Li, Loong Fah Cheong, Robby T. Tan. 2017

60 citations recorded by the source corpus.

Given a single input rainy image, our goal is to visually remove rain streaks and the veiling effect caused by scattering and transmission of rain streaks and rain droplets. We are particularly concerned with heavy rain, where rain streaks of various sizes and directions can overlap each other and the veiling effect reduces contrast severely. To achieve our goal, we introduce a scale-aware multi-stage convolutional neural network. Our main idea here is that different sizes of rain-streaks visually degrade the scene in different ways. Large nearby streaks obstruct larger regions and are likely to reflect specular highlights more prominently than smaller distant streaks. These different effects of different streaks have their own characteristics in their image features, and thus need to be treated differently. To realize this, we create parallel sub-networks that are trained and made aware of these different scales of rain streaks. To our knowledge, this idea of parallel sub-networks that treats the same class of objects according to their unique sub-classes is novel, particularly in the context of rain removal. To verify our idea, we conducted experiments on both synthetic and real images, and found that our method is effective and outperforms the state-of-the-art methods.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chunhua Shen
2. Hao Chen
3. Jianlong Wu
4. Zhouchen Lin
5. Hong Liu
6. Hongyuan Zha
7. Ying Li
8. Haokui Zhang

In Media Technology

1. Hong Liu
2. Hongyuan Zha
3. Chunhua Shen
4. Hao Chen
5. Ying Li
6. Jianlong Wu
7. Zhouchen Lin
8. Haokui Zhang

Citations in the corpus

• IR-NAS: Neural Architecture Search for Image Restoration (2019, background): “Li et al. [13] design a scale-aware multi-stage recurrent network that consists of several parallel sub-networks to estimate rain streaks of different sizes and densities individually.”
• Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining (2018, methodology): “However, recurrent structure used in their methods [9,13] can only be regarded as the simple cascade of the same network.”