/CutMIB

CutMIB in CVPR 2023

Primary LanguagePython

CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending

Zeyu Xiao, Yutong Liu, Ruisheng Gao, and Zhiwei Xiong. CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending. In CVPR 2023.

Dependencies

  • This repository is based on BasicLFSR
  • Python 3 (Recommend to use Anaconda)
  • PyTorch 1.2.0: conda install pytorch=1.2.0 torchvision cudatoolkit=9.2 -c pytorch
  • numpy: pip install numpy
  • opencv: pip install opencv-python
  • tensorboardX: pip install tensorboardX

Train the model

python training_InterNet_cutmib_x4.py

Test the model

python inference_InterNet_cutmib_x4.py

Citation

@InProceedings{Xiao_2023_cutmib,
    author    = {Xiao, Zeyu and Liu, Yutong and Gao, Ruisheng and Xiong, Zhiwei},
    title     = {CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending},
    booktitle = {CVPR},
    year      = {2023},
}

@InProceedings{Xiao_2023_toward,
    author    = {Xiao, Zeyu and Gao, Ruisheng and Liu, Yutong and Zhang, Yueyi and Xiong, Zhiwei},
    title     = {Toward Real-World Light Field Super-Resolution},
    booktitle = {CVPRW},
    year      = {2023},
}

Contact

Any question regarding this work can be addressed to zeyuxiao1997@163.com or zeyuxiao@mail.ustc.edu.cn.