English

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

Computer Vision and Pattern Recognition 2018-04-04 v4

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

Keywords

Cite

@article{arxiv.1711.07064,
  title  = {DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks},
  author = {Orest Kupyn and Volodymyr Budzan and Mykola Mykhailych and Dmytro Mishkin and Jiri Matas},
  journal= {arXiv preprint arXiv:1711.07064},
  year   = {2018}
}

Comments

CVPR 2018 camera-ready

R2 v1 2026-06-22T22:50:50.730Z