Awesome

Video Frame Synthesis using Deep Voxel Flow

We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. Deep Voxel Flow (DVF) is efficient, and can be applied at any video resolution. We demonstrate that our method produces results that both quantitatively and qualitatively improve upon the state-of-the-art.

Note: we encourage you to check out the newly released pytorch-voxel-flow. Please contact Dr. Xiaoxiao Li (lxx1991@gmail.com) for the pre-trained models of "Deep Voxel Flow".

[Project] [Paper] [Demo]

Other Implementations

Overview

Deep Voxel Flow (DVF) is the author's re-implementation of the video frame synthesizer described in:
"Video Frame Synthesis using Deep Voxel Flow"
Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala (CUHK & UIUC & Google Research) in International Conference on Computer Vision (ICCV) 2017, Oral Presentation

Further information please contact Ziwei Liu.

Requirements

TensorFlow

Data Preparation

Train/Test Split
Training Data: extract frame triplets from UCF101 with obvious motion.
Testing Data
Motion Masks

Getting started

Run the training script:

python voxel_flow_train.py --subset=train

Run the testing script:

python voxel_flow_train.py --subset=test

Run the evaluation script:

matlab eval_voxelflow.m

License and Citation

The use of this software is RESTRICTED to non-commercial research and educational purposes.

@inproceedings{liu2017voxelflow,
 author = {Ziwei Liu, Raymond Yeh, Xiaoou Tang, Yiming Liu, and Aseem Agarwala},
 title = {Video Frame Synthesis using Deep Voxel Flow},
 booktitle = {Proceedings of International Conference on Computer Vision (ICCV)},
 month = {October},
 year = {2017} 
}

Disclaimer

This is not an official Google product.