【PR'2025🔥】 DRNet: Learning a dynamic recursion network for chaotic rain streak removal

Welcome! This is the official implementation of our paper: DRNet: Learning a dynamic recursion network for chaotic rain streak removal

Authors: Zhiying Jiang, Risheng Liu, Shuzhou Yang, Zengxi Zhang, Xin Fan*.

🔑 Prerequisites

• Linux or macOS
• Python 3.8
• NVIDIA GPU + CUDA CuDNN

pip install torch h5py scikit-video

Type the command:

pip install -r requirements.txt

🤖 Training

CUDA_VISIBLE_DEVICES=0 python train.py

🚀 Inference

CUDA_VISIBLE_DEVICES=0 python test.py

📌 Citation

If you find this code useful for your research, please use the following BibTeX entry.

@article{JIANG2025111004,
title = {DRNet: Learning a dynamic recursion network for chaotic rain streak removal},
journal = {Pattern Recognition},
volume = {158},
pages = {111004},
year = {2025},
issn = {0031-3203},
doi = {https://doi.org/10.1016/j.patcog.2024.111004},
author = {Zhiying Jiang and Risheng Liu and Shuzhou Yang and Zengxi Zhang and Xin Fan}
}