Towards Unified Deep Image Deraining: A Survey and A New Benchmark

Xiang Chen             Jinshan Pan             Jiangxin Dong             Jinhui Tang

Nanjing University of Science and Technology            

Click here to submit your results

This designed online platform could serve as a reference source for future study and promote the development of the community.

The proposed platform and the collected methods, datasets, and comparison results are publicly available and will be regularly updated at this website.

Noisy Image Rainy Image
Ground Truth Image Ground Truth


Recent years have witnessed significant advances in image deraining due to the kinds of effective image priors and deep learning models. As each deraining approach has individual settings (e.g., training and test datasets, evaluation criteria), how to fairly evaluate existing approaches comprehensively is not a trivial task. Although existing surveys aim to review of image deraining approaches comprehensively, few of them focus on providing unify evaluation settings to examine the deraining capability and practicality evaluation. In this paper, we provide a comprehensive review of existing image deraining method and provide a unify evaluation setting to evaluate the performance of image deraining methods. We construct a new high-quality benchmark named HQ-RAIN to further conduct extensive evaluation, consisting of 5,000 paired high-resolution synthetic images with higher harmony and realism. We also discuss the existing challenges and highlight several future research opportunities worth exploring. To facilitate the reproduction and tracking of the latest deraining technologies for general users, we build an online platform to provide the off-the-shelf toolkit, involving the large-scale performance evaluation. This online platform and the proposed new benchmark are publicly available and will be regularly updated at


Xiang Chen, Jinshan Pan, Jiangxin Dong, Jinhui Tang. "Towards Unified Deep Image Deraining: A Survey and A New Benchmark", arXiv preprint arXiv:2310.03535 (arXiv), 2023.

[PDF]   [Bibtex]



Part of the code for this platform borrows from SIDD.


The all online resources are under the MIT License.


For any questions, remarks, comments, or collaborations, please contact: