DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

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 eval...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 8183 - 8192
Main Authors Kupyn, Orest, Budzan, Volodymyr, Mykhailych, Mykola, Mishkin, Dmytro, Matas, Jiri
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Convolution
Gallium nitride
Generative adversarial networks
Generators
Image restoration
Kernel
Training
Online AccessGet full text

Cover

More Information
Summary: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 - Deep-Deblur [25]. 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
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00854