|
ИСТИНА |
Войти в систему Регистрация |
Интеллектуальная Система Тематического Исследования НАукометрических данных |
||
Depth-Aware Arbitrary Style Transfer Using Instance Normalizationстатья
Информация о цитировании статьи получена из
Scopus
Дата последнего поиска статьи во внешних источниках: 18 марта 2021 г.
- Авторы: Kitov Victor, Kozlovtsev Konstantin, Mishustina Margarita
- Сборник: CEUR WORKSHOP PROCEEDINGS
- Серия: "Proceedings of the 30th International Conference on Computer Graphics and Machine Vision,Saint Petersburg, Russia, ITMO 2020."
- Том: 2744
- Год издания: 2020
- Место издания: MONOMAX Limited Liability Company ITMO University, Saint Petersburg, Russia
- DOI: 10.51130/graphicon-2020-2-3-2
- Аннотация: Style transfer is the process of rendering one image with some content in the style of another image, representing the style. Recent studies of Liu et al. (2017) show that traditional style transfer methods of Gatys et al. (2016) and Johnson et al. (2016) fail to reproduce the depth of the content image, which is critical for human perception. They suggest to preserve the depth map by additional regularizer in the optimized loss function, forcing preservation of the depth map. However these traditional methods are either computationally inefficient or require training a separate neural network for each style. AdaIN method of Huang et al. (2017) allows efficient transferring of arbitrary style without training a separate model but is not able to reproduce the depth map of the content image. We propose an extension to this method, allowing depth map preservation by applying variable stylization strength. Qualitative analysis and results of user evaluation study indicate that the proposed method provides better stylizations, compared to the original AdaIN style transfer method.
- Добавил в систему: Китов Виктор Владимирович