Single Image Deraining via Recurrent Hierarchy Enhancement Network (ACMMM'2019)
@inproceedings{yang2019single,
title={Single image deraining via recurrent hierarchy enhancement network},
author={Yang, Youzhao and Lu, Hong},
booktitle={Proceedings of the 27th ACM International Conference on Multimedia},
pages={1814--1822},
year={2019}
}
Quantitative Result
The metrics are PSNR/SSIM. Both are evaluated on RGB channels.
| Method | Rain200L | Rain200H | Rain800 | Rain1200 | Rain1400 |
|---|---|---|---|---|---|
| rehen_c24s4n5 | 38.06/0.983 | 27.76/0.868 | 26.83/0.849 | 32.28/0.907 | 31.22/0.914 |
Pretrained models can be downloaded from here
Network Complexity
| Input shape | Flops | Params |
|---|---|---|
| (3, 256, 256) | 71.05GFlops | 297.96k |