KEEP: Kalman-Inspired Feature Propagation for Video Face Super-Resolution

Official Gradio demo for Kalman-Inspired FEaturE Propagation for Video Face Super-Resolution (ECCV 2024).
🔥 KEEP is a robust video face super-resolution algorithm.
🤗 Try to drop your own face video, and get the restored results!

If you found KEEP helpful, please consider ⭐ the Github Repo. Thanks!

📝 Citation
If our work is useful for your research, please consider citing:

@InProceedings{feng2024keep,
      title     = {Kalman-Inspired FEaturE Propagation for Video Face Super-Resolution},
      author    = {Feng, Ruicheng and Li, Chongyi and Loy, Chen Change},
      booktitle = {European Conference on Computer Vision (ECCV)},
      year      = {2024}
}

📋 License
This project is licensed under S-Lab License 1.0. Redistribution and use for non-commercial purposes should follow this license.

📧 Contact
If you have any questions, please feel free to reach out via ruicheng002@ntu.edu.sg.