Видалення тіней із зображення за допомогою генеративних  змагальних мереж та навчання без учителя

dc.contributor.advisor	Бучко, Олена
dc.contributor.author	Андронік, Владислав
dc.date.accessioned	2020-11-12T20:49:35Z
dc.date.available	2020-11-12T20:49:35Z
dc.date.issued	2020
dc.description.abstract	This material presents the solution for shadow removal task using generative adversarial networks. Our approach is trained in unsupervised fashion which means it does not depend on time-consuming data collection and annotation. This together with training in a single end-to-end framework significantly raises its practical relevance. Taking the existing method for unsupervised image transfer between different domains we researched its applicability to the shadow removal problem. By exploiting attention modules and multi context feature aggregation using dilated convolutions our method gives significant results compared to existing solutions in the field.	uk_UA
dc.identifier.uri	https://ekmair.ukma.edu.ua/handle/123456789/18658
dc.language.iso	en	uk_UA
dc.status	first published	uk_UA
dc.subject	generative adversarial networks	uk_UA
dc.subject	unsupervised learning	uk_UA
dc.subject	shadow removal	uk_UA
dc.subject	shadow generation	uk_UA
dc.subject	attention module	uk_UA
dc.subject	dilated convolutions	uk_UA
dc.subject	курсова робота	uk_UA
dc.title	Видалення тіней із зображення за допомогою генеративних змагальних мереж та навчання без учителя	uk_UA
dc.type	Other	uk_UA

Now showing 1 - 2 of 2

Now showing 1 - 1 of 1