Frame-Recurrent Video Super-Resolution (official repository)
This is the official repository for the Frame-Recurrent Video Super-Resolution project by Mehdi S. M. Sajjadi, Raviteja Vemulapalli and Matthew Brown, presented at CVPR 2018.
(left: low-resolution input, middle: FRVSR output, right: high-resolution ground truth)
https://vimeo.com/album/5053944
https://people.tuebingen.mpg.de/msajjadi/FRVSR_Vid4.zip
youtube-dl -civ --batch-file=dataset_train.txt
Please note that some of the videos may be unavailable by now.
@inproceedings{frvsr,
title={{Frame-Recurrent Video Super-Resolution}},
author={Sajjadi, Mehdi S. M. and Vemulapalli, Raviteja and Brown, Matthew},
booktitle = {{The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}},
month = {June},
year={2018}
}
For any questions, comments or help to get it to run, please don't hesitate to mail us: [email protected]