ML Anthology

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiří Matas
CVPR 2018
doi:10.1109/CVPR.2018.00854 /cvpr/2018/kupyn2018cvpr-deblurgan/

Abstract

We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss . DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images. The method is 5 times faster than the closest competitor -- DeepDeblur. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN

PDF CVPR Semantic Scholar

Cite

Text

Kupyn et al. "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00854

Markdown

[Kupyn et al. "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/kupyn2018cvpr-deblurgan/) doi:10.1109/CVPR.2018.00854

BibTeX

@inproceedings{kupyn2018cvpr-deblurgan,
  title     = {{DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks}},
  author    = {Kupyn, Orest and Budzan, Volodymyr and Mykhailych, Mykola and Mishkin, Dmytro and Matas, Jiří},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00854},
  url       = {https://mlanthology.org/cvpr/2018/kupyn2018cvpr-deblurgan/}
}