The official pytorch implementation of the paper Revitalizing Convolutional Network for Image Restoration
All resulting images and pre-trained models are available in the provided links.
11/26/2024 Code for real haze and haze4k are released.
07/22/2024 We release the code for dehazing (ITS/OTS), desnowing, deraining, and motion deblurring.
The project is built with PyTorch 3.8, PyTorch 1.8.1. CUDA 10.2, cuDNN 7.6.5 For installing, follow these instructions:
conda install pytorch=1.8.1 torchvision=0.9.1 -c pytorch
pip install tensorboard einops scikit-image pytorch_msssim opencv-python
Please use the pillow package downloaded by Conda rather than pip.
Install warmup scheduler:
cd pytorch-gradual-warmup-lr/
python setup.py install
cd ..
Please refer to respective directories.
| Model | Parameters | FLOPs |
|---|---|---|
| ConvIR-S (small) | 5.53M | 42.1G |
| ConvIR-B (base) | 8.63M | 71.22G |
| ConvIR-L (large) | 14.83M | 129.34G |
@article{cui2024revitalizing,
title={Revitalizing Convolutional Network for Image Restoration},
author={Cui, Yuning and Ren, Wenqi and Cao, Xiaochun and Knoll, Alois},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2024},
publisher={IEEE}
}
@inproceedings{cui2023irnext,
title={IRNeXt: Rethinking Convolutional Network Design for Image Restoration},
author={Cui, Yuning and Ren, Wenqi and Yang, Sining and Cao, Xiaochun and Knoll, Alois},
booktitle={International Conference on Machine Learning},
pages={6545--6564},
year={2023},
organization={PMLR}
}
Should you have any problem, please contact Yuning Cui.