Conditional Adversarial Networks for Blind Image Deblurring

dc.contributor.author	Kupyn, Orest
dc.date.accessioned	2018-01-23T23:55:46Z
dc.date.available	2018-01-23T23:55:46Z
dc.date.issued	2018
dc.identifier.citation	Kupyn, Orest. Conditional Adversarial Networks for Blind Image Deblurring : Master Thesis : manuscript rights / Orest Kupyn ; Supervisor Dr. Rostyslav Hryniv ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2017. – 44 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/1189
dc.description.abstract	We present an end-to-end learning approach for motion deblurring, which is based on conditional GAN and content loss – DeblurGAN. DeblurGAN achieves state-of-the art in structural similarity measure and by 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. Second, we present a novel method of generating synthetic motion blurred images from the sharp ones, which allows realistic dataset augmentation.	uk
dc.language.iso	en	uk
dc.subject	Conditional Adversarial Networks	uk
dc.subject	DeblurGAN	uk
dc.title	Conditional Adversarial Networks for Blind Image Deblurring	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk