DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

被引：1183

作者：

Kupyn, Orest ^{[1
,3
]}

Budzan, Volodymyr ^{[1
,3
]}

Mykhailych, Mykola ^{[1
]}

Mishkin, Dmytro ^{[2
]}

Matas, Jiri ^{[2
]}

机构：

[1] Ukrainian Catholic Univ, Lvov, Ukraine

[2] Czech Tech Univ, FEE, Ctr Machine Percept, Visual Recognit Grp, Prague, Czech Republic

[3] ELEKS Ltd, Lvov, Ukraine

来源：

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年

关键词：

D O I：

10.1109/CVPR.2018.00854

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 J. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation.

引用

页码：8183 / 8192

页数：10