https://github.com/shuochsu/DeepVideoDeblurring
S. Su, M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, O. Wang. Deep Video Deblurring. CVPR 2017, Spotlight
https://github.com/shuochsu/DeepVideoDeblurring
convolutional-neural-networks deblurring deep-learning video
Last synced: 12 days ago
JSON representation
S. Su, M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, O. Wang. Deep Video Deblurring. CVPR 2017, Spotlight
- Host: GitHub
- URL: https://github.com/shuochsu/DeepVideoDeblurring
- Owner: shuochsu
- License: mit
- Created: 2017-03-06T07:47:55.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2019-04-02T18:34:05.000Z (about 7 years ago)
- Last Synced: 2024-11-27T08:36:16.831Z (over 1 year ago)
- Topics: convolutional-neural-networks, deblurring, deep-learning, video
- Language: MATLAB
- Homepage: http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/
- Size: 1.39 MB
- Stars: 191
- Watchers: 12
- Forks: 63
- Open Issues: 7
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
Awesome Lists containing this project
- awesome-github-projects - DeepVideoDeblurring - S. Su, M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, O. Wang. Deep Video Deblurring. CVPR 2017, Spotlight ⭐194 `MATLAB` (📦 Legacy & Inactive Projects)
README
## Deep Video Deblurring for Hand-held Cameras
This is the demo code for [Deep Video Deblurring for Hand-held Cameras](http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/). Given a stack of pre-aligned input frames, our network predicts a sharper central image.
### Prepare data
- Download and unzip test videos to `dataset`, from this [link](http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/DeepVideoDeblurring_Dataset.zip), or place your own test video frames under `dataset/qualitative_datasets/[video_file_name]/input`.
- Align frames in Matlab, by running
```Shell
preprocess/launcher.m
```
Outputs should be stored at `data/testing_real_all_nostab_[alignment]` under structure
```Shell
/image_-2
/image_-1
/image_0
/image_1
/image_2
```
Alternatively, you can download the pre-aligned qualitative videos from [here](http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/testing_real_all_nostab_OF.zip), [here](http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/testing_real_all_nostab_homography.zip), and [here](http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/testing_real_all_nostab_nowarp.zip).
### Download pretrained weights
- Download and unzip pretrained weights into `logs`, from [here](http://www.cs.ubc.ca/labs/imager/tr/2017/DeepVideoDeblurring/pretrained.zip).
### Run prediction script
- Run script: `sh run_pred.sh`
- Results will be saved to `outImg`.
### FAQ
- split of the training/test sets: https://github.com/shuochsu/DeepVideoDeblurring/issues/2#issuecomment-312954167
### Citation
If you find this code useful for your research, please cite:
```
@inproceedings{su2017deep,
title={Deep Video Deblurring for Hand-held Cameras},
author={Su, Shuochen and Delbracio, Mauricio and Wang, Jue and Sapiro, Guillermo and Heidrich, Wolfgang and Wang, Oliver},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={1279--1288},
year={2017}
}
```