EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining

Authors

  • Qing Guo Nanyang Technological University, Singapore
  • Jingyang Sun Kyushu University, Japan
  • Felix Juefei-Xu Alibaba Group, USA
  • Lei Ma Kyushu University, Japan
  • Xiaofei Xie Nanyang Technological University, Singapore
  • Wei Feng College of Intelligence and Computing, Tianjin University, China
  • Yang Liu Nanyang Technology University, Singapore
  • Jianjun Zhao Kyushu University, Japan

DOI:

https://doi.org/10.1609/aaai.v35i2.16239

Keywords:

Low Level & Physics-based Vision, Applications, General

Abstract

Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, compelling them to employ complex optimization or progressive refinement. This, however, significantly affects these methods' efficiency and effectiveness for many efficiency-critical applications. To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i.e., EfficientDeRain, which is able to process a rainy image within 10 ms (i.e., around 6 ms on average), over 80 times faster than the state-of-the-art method (i.e., RCDNet), while achieving similar de-rain effects. We first propose novel pixel-wise dilation filtering. In particular, a rainy image is filtered with the pixel-wise kernels estimated from a kernel prediction network, by which suitable multi-scale kernels for each pixel can be efficiently predicted. Then, to eliminate the gap between synthetic and real data, we further propose an effective data augmentation method (i.e., RainMix) that helps to train the network for handling real rainy images. We perform a comprehensive evaluation on both synthetic and real-world rainy datasets to demonstrate the effectiveness and efficiency of our method. We release the model and code in https://github.com/tsingqguo/efficientderain.git.

Downloads

Published

2021-05-18

How to Cite

Guo, Q., Sun, J., Juefei-Xu, F., Ma, L., Xie, X., Feng, W., Liu, Y., & Zhao, J. (2021). EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1487-1495. https://doi.org/10.1609/aaai.v35i2.16239

Issue

Section

AAAI Technical Track on Computer Vision I