This repository is a PyTorch implementation of the paper "Learning to Extract a Video Sequence from a Single Motion-Blurred Image" from CVPR 2018 [paper][arxiv][supplementary][video examples].

If you find our work useful in your research or publication, please cite our work:

@InProceedings{Jin_2018_CVPR,
author = {Jin, Meiguang and Meishvili, Givi and Favaro, Paolo},
title = {Learning to Extract a Video Sequence From a Single Motion-Blurred Image},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}

Requirements

The code is based on Python 2.7 and Pytorch 0.3.0.

Test

Download pretrained models from here.

python demo.py --cuda --input input.png

Training

To be updated

Contact

If you have any suggestions and questions, please send an email to jinmeiguang@gmail.com