HRGAN: High-Resolution Representation  Learning for Image Deblurring

dc.contributor.author	Borsuk, Vasyl
dc.date.accessioned	2024-02-15T08:31:25Z
dc.date.available	2024-02-15T08:31:25Z
dc.date.issued	2020
dc.identifier.citation	Borsuk, Vasyl. HRGAN: High-Resolution Representation Learning for Image Deblurring / Borsuk, Vasyl; Supervisor: Orest Kupyn; Ukrainian Catholic University, Department of Computer Sciences. – Lviv: 2020. – 39 p.	uk
dc.identifier.uri	https://er.ucu.edu.ua/handle/1/4496
dc.language.iso	en	uk
dc.title	HRGAN: High-Resolution Representation Learning for Image Deblurring	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Existing state-of-the-art single-image motion deblurring frameworks first encode the input image as a semantically rich low-resolution representation and then recover the high-resolution image from this representation. The network which generates an image from low-resolution features is not the right choice for pixel-level predic- tions as it fails to recover finer texture details. We introduce the idea of the High- Resolution Network (HRNet) to image deblurring. It maintains high-resolution rep- resentation through the whole process instead of recovering high resolution from low resolution. Additionally, we propose to use the CutMix augmentation strategy to enhance the performance of our network.	uk