JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation

The official PyTorch implementation of JNMR.

Authors: Meiqin Liu, Chenming Xu, Chao Yao*, Chunyu Lin, Yao Zhao

Meiqin Liu and Chenming Xu have made equal contributions to this research.

Baseline

There is our proposed baseline of JNMR for four reference frames interpolation. The code of JNMR is coming soon.

Acknowledgement

The implementation is based on AdaCoF and CDFI.

Citation

If you find this work useful for your research, please cite:

@inproceedings{lee2020adacof,
    title={AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation},
    author={Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2020}
}
@inproceedings{ding2021cdfi,
  title={Cdfi: Compression-driven network design for frame interpolation},
  author={Ding, Tianyu and Liang, Luming and Zhu, Zhihui and Zharkov, Ilya},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={8001--8011},
  year={2021}
}
@article{liu2022jnmr,
  title={JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation},
  author={Liu, Meiqin and Xu, Chenming and Yao, Chao and Lin, Chunyu and Zhao, Yao},
  journal={arXiv preprint arXiv:2206.04231},
  year={2022}
}