Пошук академічних текстів

Інформація × Реєстраційний номер 2120U007853, Матеріали видань та локальних репозитаріїв Категорія Препринт Назва роботи Face reenactment with GANs using landmark representation of a face Автор Kosarevych IvanKosarevych Ivan Дата публікації 01-01-2020 Постачальник інформації Український католицький університет Першоджерело https://hdl.handle.net/20.500.14570/4512 Видання Опис 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. Додано в НРАТ 2025-11-05 Закрити