Skip to content

This repo is the official pytorch implement for LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution (CVPR, 2021).

License

Notifications You must be signed in to change notification settings

culiver/LAU-Net

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution (CVPR, 2021) [pdf]

Pytorch implementation for "LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution".

Dependencies

Python=3.7, PyTorch=1.7.0, numpy, skimage, cv2, matplotlib, tqdm

Test scripts

Put dataset in ./dataset.

Put pre-trained model in ./results/model.

Run the main.py:

python main.py --test_only --datastest=test --pre_train='./results/model/model_best.pt'

ODI-SR and testing datasets

Google Drive:

link: https://drive.google.com/drive/folders/1w7m1r-yCbbZ7_xMGzb6IBplPe4c89rH9?usp=sharing

Pretrained model

Google Drive:

link: https://drive.google.com/drive/folders/15FxJOB0hWR3WZTg9CNxKKjGciQF8ZwSK?usp=sharing

Citation

If you find our paper or code useful for your research, please cite:

@InProceedings{Deng_2021_CVPR,
    author    = {Deng, Xin and Wang, Hao and Xu, Mai and Guo, Yichen and Song, Yuhang and Yang, Li},
    title     = {LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-Resolution},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {9189-9198}
}

Contact

If you have any problem, please contact with me through email. I will reply soon.

My email: [email protected]

About

This repo is the official pytorch implement for LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution (CVPR, 2021).

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%