|
ИСТИНА |
Войти в систему Регистрация |
ФНКЦ РР |
||
Method for Enhancing High-Resolution Image Inpainting with Two-Stage Approachстатья
Информация о цитировании статьи получена из
Web of Science,
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 20 октября 2021 г.
- Авторы: Moskalenko A., Erofeev M., Vatolin D.
- Журнал: Programming and Computer Software
- Том: 47
- Номер: 3
- Год издания: 2021
- Издательство: Pleiades Publishing, Ltd
- Местоположение издательства: Road Town, United Kingdom
- Первая страница: 201
- Последняя страница: 206
- DOI: 10.1134/s0361768821030075
- Аннотация: In recent years, the field of image inpainting has developed rapidly, learning based approaches show impressive results in the task of filling missing parts in an image. But most deep methods are strongly tied to the resolution of the images on which they were trained. A slight resolution increase leads to serious artifacts and unsatisfactory filling quality. These methods are therefore unsuitable for interactive image processing. In this article, we propose a method that solves the problem of inpainting arbitrary-size images. We also describe a way to better restore texture fragments in the filled area. For this, we propose to use information from neighboring pixels by shifting the original image in four directions. Moreover, this approach can work with existing inpainting models, making them almost resolution independent without the need for retraining.
- Добавил в систему: Москаленко Андрей Викторович
Прикрепленные файлы
| № | Имя | Описание | Имя файла | Размер | Добавлен |
|---|---|---|---|---|---|
| 1. | Полный текст | Paper.pdf | 1,3 МБ | 27 декабря 2021 [MoskalenkoAV] |