Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation

Code for the paper IC-FSRDENet.

Requirement

Pytorch 1.11.0 Cuda 11.4

Train IC-FSRNet model:

cd IC-FSRNet
python train.py --dir_data dir_data --writer_name icfsrnet --model MYNET 

Test IC-FSRNet:

cd IC-FSRNet
python test.py --dir_data dir_data --data_test test --writer_name icfsrnet-test --model MYNET 

Train DENet model:

cd DENet
python train.py  -c config/denet.json

Test DENet:

cd DENet
python test.py -c config/denet_test.json

Test Dataset

BaiDu passward:x6y7

Pretrained Model

BaiDu passward:ywqj

Citation

@InProceedings{Wang_2024_AAAI,
    author    = {Wang, Chenyang and Jiang, Junjun and Jiang, Kui and Liu, Xianming},
    title     = {Spatial-Frequency Mutual Learning for Face Super-Resolution},
    booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
    year      = {2024},
}