Region-Selected Image Generation with Generative Adversarial Networks

Korshunov, Vadym

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2020
→
Перегляд матеріалів

dc.contributor.author	Korshunov, Vadym
dc.date.accessioned	2020-02-25T10:46:16Z
dc.date.available	2020-02-25T10:46:16Z
dc.date.issued	2020
dc.identifier.citation	Korshunov, Vadym. Region-Selected Image Generation with Generative Adversarial Networks : Master Thesis : manuscript / Vadym Korshunov ; Supervisor Dmytro Mishkin ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 54 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/2049
dc.language.iso	en	uk
dc.subject	Region-Selected Image Generation	uk
dc.subject	Generative Adversarial Networks	uk
dc.subject	Region-selected manipulation models	uk
dc.title	Region-Selected Image Generation with Generative Adversarial Networks	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Generative adversarial networks (GANs) are one of the most popular models capable of producing high-quality images. However, most of the works generate images from the vector of random values, without explicit control of desired output properties. We study the ways of introducing such control for the user-selected region of interest (RoI). First, we overview and analyze the existing works in areas of image completion (inpainting) and controllable generation. Second, we propose our model based on GANs, which united approaches from the two mentioned areas, for the controllable local content generation. Third, we evaluate the controllability of our model on three accessible datasets – Celeba, Cats, and Cars – and give numerical and visual results of our method.	uk