UDUTV(ECCV 2022, Oral presentation)

This repository is for the ECCV 2022 paper, "Event-guided Deblurring of Unknown Exposure Time Videos".

[ArXiv] [ECCV2022] [Supp] [Oral(YouTube)] [Project]

Demo videos on real world blurry videos

Table of Contents

1. Color-DVS
2. Installation
3. Test
4. Test_Custom
5. Training
6. Results
7. Reference
8. Contact

Color-DVS

The first public event-based deblurring dataset. Our dataset contain diverse scene including real-world event using color-DAVIS camera.

You can download the raw-data(collected frame and events) from this google drive link

Also, you can download the processed data for handling unknown exposure time videos link

Installation

This code was tested with:

• pytorch 1.2.0
• CUDA 10.2
• Python 3.7
• Ubuntu 18.04 using TITAN RTX GPU

pip install -r requirements.txt
bash install.sh

Test

python test_deblur_dvs.py --dataset 'dvs'

Training

python train_deblur_dvs.py --dataset 'dvs' --epochs 21 --batch_size 2 \
--test_batch_size 1 --use_multigpu True

Results

Reference

Taewoo Kim, Jeongmin Lee, Lin Wang, and Kuk-Jin Yoon" Event-guided Deblurring of Unknown Exposure Time Videos", In ECCV, 2022.

BibTeX

@article{kim2021event,
  title={Event-guided Deblurring of Unknown Exposure Time Videos},
  author={Kim, Taewoo and Lee, Jungmin and Wang, Lin and Yoon, Kuk-Jin},
  journal={arXiv preprint arXiv:2112.06988},
  year={2021}
}

Contact

If you have any question, please send an email me(intelpro@kaist.ac.kr)

License

The project codes and datasets can be used for research and education only.