GitHub - kyrie111/EFINet (original) (raw)

EFINet: Restoration for Low-light Images via Enhancement-Fusion Iterative Network

python 3.7  
torch 1.4.0  
torchvision 0.2.1  
cuda 10.1  
numpy  
opencv

The results will be saved at data/result.

The script processes images located in the subfolders of the test_data directory and creates a new result folder within the data directory. The enhanced images will be available in the result folder.

@ARTICLE{liu2022efinet,
  title={EFINet: Restoration for Low-light Images via Enhancement-Fusion Iterative Network}, 
  author={Liu, Chunxiao and Wu, Fanding and Wang, Xun},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  year={2022},
  volume={32},
  number={12},
  pages={8486-8499},
  doi={10.1109/TCSVT.2022.3195996}}