Показати скорочений опис матеріалу
dc.contributor.author | Kusyy, Andriy![]() |
|
dc.date.accessioned | 2019-02-19T14:37:22Z | |
dc.date.available | 2019-02-19T14:37:22Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Kusyy, Andriy. Color and style transfer using Generative Adversarial Networks : Master Thesis : manuscript / Andriy Kusyy ; Supervisor Dr. Rostyslav Hryniv ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2019. – 30 p. : ill. | uk |
dc.identifier.uri | http://er.ucu.edu.ua/handle/1/1331 | |
dc.language.iso | en | uk |
dc.subject | Generative Adversarial Networks | uk |
dc.subject | Dataset and preprocessing | uk |
dc.subject | Generative Model | uk |
dc.title | Color and style transfer using Generative Adversarial Networks | uk |
dc.type | Preprint | uk |
dc.status | Публікується вперше | uk |
dc.description.abstracten | In this work, we present an end-to-end solution for an image to image color and style transfer using Conditional Generative Adversarial Networks. Nowadays photo editing industry is growing rapidly, and one of the crucial issues is recoloring and restyling of individual objects or areas on images. With a fast advancement of deep segmentation models, getting a precise segmentation mask for an area on a picture is no longer a problem although unsupervised restyling and recoloring of the object with complex patterns is still a challenge. The proposed model is a state-of-the-art regarding visual appearance and provides high structural similarity. | uk |