DeblurGAN: Blind motion deblurring using conditional adversarial networks

Autoren Orest Kupyn
Volodymyr Budzan
Mykola Mykhailych
Dmytro Mishkin
Jiri Matas
Editoren
Titel DeblurGAN: Blind motion deblurring using conditional adversarial networks
Buchtitel Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018)
Typ Konferenzband
Ort IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
ISBN 978-1-5386-6420-9
DOI 10.1109/CVPR.2018.00854
Monat December
Jahr 2018
Seiten 8183-8192
SCCH ID# 17090
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.