Introduction | Datasets | Results
Single image deraining (SID) in real scenarios attracts increasing attention in recent years. Due to the difficulty in obtaining real-world rainy/clean image pairs, previous real datasets suffer from low-resolution images, homogeneous rain streaks, limited background variation, and even misalignment of image pairs, resulting in incomprehensive evaluation of SID methods. To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of 1,120 high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively. Images in RealRain-1k are automatically generated from a large number of real-world rainy video clips through a simple yet effective rain density-controllable filtering method, and have good properties of high image resolution, background diversity, rain streaks variety, and strict spatial alignment. RealRain-1k also provides abundant rain streak layers as a byproduct, enabling us to build a large-scale synthetic dataset named SynRain-13k by pasting the rain streak layers on abundant natural images. Based on them and existing datasets, we benchmark more than 10 representative SID methods on three tracks: (1) fully supervised learning on RealRain-1k, (2) domain generalization to real datasets, and (3) syn-to-real transfer learning. The experimental results (1) show the difference of representative methods in image restoration performance and model complexity, (2) validate the significance of the proposed datasets for model generalization, and (3) provide useful insights on the superiority of learning from diverse domains and shed lights on the future research on real-world SID.
A glance at other real rainy datasets and RealRain-1k. RealRain-1k and SyRain-13k have been released at here. We will extend RealRain-1k to higher quality derain dataset in the future!
-
Benchmark results of supervised learning track
-
Some visual results of syn2real domain generalization track
-
Some visual results of real2real domain generalization track
If you are interested in our work, please consider citing the following:
@article{li2022toward,
title={Toward Real-world Single Image Deraining: A New Benchmark and Beyond},
author={Li, Wei and Zhang, Qiming and Zhang, Jing and Huang, Zhen and Tian, Xinmei and Tao, Dacheng},
journal={arXiv preprint arXiv:2206.05514},
year={2022}
}