This is official implementation of NIRNet, which is implemented on MMRotate.
Note: We will be updating the code in the near future.
Some examples of the Hazy-DIOR dataset.
🛎️NOTE:
The dataset is avaliable from Google Drive or Baidu Netdisk.
Please refer to the markdown for installation and dataset preparation.
train
cd nirnet
python tools/train.py ./config/nirnet_r50_1x_dior_le135.py
test
cd nirnet
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
If you find this work helpful, we would be grateful if you could cite it:
@article{zhang2025nirnet,
title={NIRNet: Noise Incentive Robust Network in Remote Sensing Object Detection Under Cloud Corruption},
author={Zhang, Peng and Cheng, Gong and Lang, Chunbo and Xie, Xingxing and Han, Junwei},
journal={IEEE Transactions on Geoscience and Remote Sensing},
volume={},
number={},
pages={1--13},
year={2025},
publisher={IEEE}
}