Awesome

<b><i>ICCV 2023</i></b>

This the official repository of the paper MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions <br> for Continuous Space-Time Video Super-Resolution.

For more information, please visit our project website.

Authors: Yi-Hsin Chen*, Si-Cun Chen*, Yi-Hsin Chen, Yen-Yu Lin, Wen-Hsiao Peng

Abstract

This work addresses continuous space-time video super-resolution (C-STVSR) that aims to up-scale an input video both spatially and temporally by any scaling factors. One key challenge of C-STVSR is to propagate information temporally among the input video frames. To this end, we introduce a space-time local implicit neural function. It has the striking feature of learning forward motion for a continuum of pixels. We motivate the use of forward motion from the perspective of learning individual motion trajectories, as opposed to learning a mixture of motion trajectories with backward motion. To ease motion interpolation, we encode sparsely sampled forward motion extracted from the input video as the contextual input. Along with a reliability-aware splatting and decoding scheme, our framework, termed MoTIF, achieves the state-of-the-art performance on C-STVSR.

Code

Test code draft available.

Testing

1. Install all the dependencies.
2. Download pretrained weights.
3. Edit test.yml for different datasets.
4. Run

python test.py

Pre-trained weights

best.pth

Citation

If you find this work useful in your research, please consider citing:

@inproceedings{chen2023MoTIF,
  title={MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution},
  author={Yi-Hsin Chen, Si-Cun Chen, Yi-Hsin Chen, Yen-Yu Lin, Wen-Hsiao Peng},
  booktitle={ICCV},
  year={2023}
}

Contact

If you have any questions, please contact Si-Cun Chen (sicun.mapl.cs09@nycu.edu.tw)