By Jiaxin Gao, Ziyu Yue, Yaohua Liu, Sihan Xie, Xin Fan, Risheng Liu

# Install basicsr - https://github.com/xinntao/BasicSR
pip install basicsr
pip install facexlib gfpgan
pip install -r requirements.txt
python setup.py develop

RELLISUR dataset: Andreas Aakerberg, Kamal Nasrollahi, Thomas Moeslund. "RELLISUR: A Real Low-Light Image Super-Resolution Dataset". NeurIPS Datasets and Benchmarks 2021. RELLISUR

Please refer to DARK FACE dataset: Yang, Wenhan and Yuan, Ye and Ren, Wenqi and Liu, Jiaying and Scheirer, Walter J. and Wang, Zhangyang and Zhang, and et al. "DARK FACE: Face Detection in Low Light Condition". IEEE Transactions on Image Processing, 2020. DARK FACE

Please refer to Dark Zurich dataset: Christos Sakaridis, Dengxin Dai, Luc van Gool. "Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation". ICCV, 2019. Dark Zurich

You can download our pre-trained model from [Google Drive] and [Baidu Yun (extracted code:cjzk)]

Depending on the task you want to execute, choose the appropriate command: For 2x Scaling Task Run the following command to start training the 2x scaling task:

sh train.sh Super_Resolution/Options/CSDLLSR_v9_7_5_3_scale2.yml

For 4x Scaling Task Run the following command to start training the 4x scaling task:

sh train.sh Super_Resolution/Options/CSDLLSR_v9_7_5_3_scale4.yml    

sh test.sh Super_Resolution/Options/CSDLLSR_v9_7_5_3_scale2_test.yml

sh test.sh Super_Resolution/Options/CSDLLSR_v9_7_5_3_scale4_test.yml    

• Visual comparison

• Benchmark Evaluation

If you use this code or ideas from the paper for your research, please cite our paper:

@article{10614925,
  title={A Dual-Stream-Modulated Learning Framework for Illuminating and Super-Resolving Ultra-Dark Images},
  author={Gao, Jiaxin and Yue, Ziyu and Liu, Yaohua and Xie, Sihan and Fan, Xin and Liu, Risheng},
  journal={IEEE Transactions on Neural Networks and Learning Systems },
  pages={1-14},
  year={2024},
  publisher={IEEE}
}

Part of the code is adapted from previous works: Restormer and BasicSR (code structure). We thank all the authors for their contributions.

Please contact me if you have any questions at: jiaxinn.gao@outlook.com