Skip to content

The Dataset and the Code for the paper "Deep Motion Blind Video Stabilization".

Notifications You must be signed in to change notification settings

MKashifAli/Motion_Blind_Video_Stabilization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

Deep Motion Blind Video Stabilization

Paper-BMVC | Download the paper [here]

The Dataset can be downloaded from this link

Test scripts

Download the model checkpoints (all stages) from this link

  1. Extract the model checkpoints to the root directory.
  2. Place the frames for videos in folders in the following format and pass the path to the folder containing videos (split into frames) to root.

Directory Structure

root
└───videos_to_test
│   └───Video_1
|   |   │   │   xxxx.png
|   |   │   │   xxxx.png
|   |   │   └───...
│   └───Video_2
|   |   │   │   xxxx.png
|   |   │   │   xxxx.png
|   |   │   └───...
│   └───Video_3
|   |   │   │   xxxx.png
|   |   │   │   xxxx.png
|   |   │   └───...
  1. Modify the test_only.py according to the stage that you would like to test. (both checkpoint name and the function name to load the models).
  2. The folder for output will be generated according to the checkpoint name.

Citation

If you find this useful for your research, please cite the following paper:

@article{ali2020deep,
  title={Deep Motion Blind Video Stabilization},
  author={Ali, Muhammad Kashif and Yu, Sangjoon and Kim, Tae Hyun},
  journal={arXiv preprint arXiv:2011.09697},
  year={2020}
}

About

The Dataset and the Code for the paper "Deep Motion Blind Video Stabilization".

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages