Face reenactment with GANs using landmark representation of a face

dc.contributor.author	Kosarevych, Ivan
dc.date.accessioned	2024-02-15T09:20:34Z
dc.date.available	2024-02-15T09:20:34Z
dc.date.issued	2020
dc.identifier.citation	Kosarevych, Ivan. Face reenactment with GANs using landmark representation of a face / Kosarevych, Ivan; Supervisor: Volodymyr Karpiv; Ukrainian Catholic University, Department of Computer Sciences. – Lviv: 2020. – 48 p.	uk
dc.identifier.uri	https://er.ucu.edu.ua/handle/1/4512
dc.language.iso	en	uk
dc.title	Face reenactment with GANs using landmark representation of a face	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Face reenactment is an emerging technology that attracts high interest in recent years. It aims at generating face with the identity of one person (known as target) and facial expression from another (source). Many existing methods are limited to reenact a predefined personality of either source or target. In this study, we present the approach that is agnostic to the identity of source and target and observes only a single image of each of them. Our method is based on recently introduced Gen- erative adversarial networks (GANs). We experimentally find a proper GAN loss for our system. An accurate expression transfer from a source person is essential for face reenactment. In this study, we examine different approaches to achieve it and design a landmark loss function based on our novel landmark detector.	uk