Official implement of Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring
conda env create --file environment.yml
conda activate FourierDiff
download this model(from guided-diffusion) and put it into FourierDiff/exp/logs/imagenet/.
wget https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_diffusion_uncond.pt
The input image should be in FourierDiff/exp/datasets/test/low.
The results should be in FourierDiff/exp/image_samples/output.
python main.py --config llve.yml --path_y test -i output
- low-light enhancement branch
- deblurring branch
@inproceedings{lv2024fourier,
title={Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring},
author={Lv, Xiaoqian and Zhang, Shengping and Wang, Chenyang and Zheng, Yichen and Zhong, Bineng and Li, Chongyi and Nie, Liqiang},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={25378--25388},
year={2024}
}