|
ИСТИНА |
Войти в систему Регистрация |
ФНКЦ РР |
||
Neural-Network-Based Detection Methods for Color, Sharpness, and Geometry Artifacts in Stereoscopic and VR180 Videosстатья
- Авторы: Lavrushkin Sergey, Kozhemyakov Konstantin, Vatolin Dmitriy
- Сборник: 2020 International Conference on 3D Immersion (IC3D)
- Год издания: 2020
- Место издания: IEEE
- DOI: 10.1109/ic3d51119.2020.9376385
- Аннотация: Shooting video in 3D format can introduce stereoscopic artifacts, potentially causing viewers visual discomfort. In this work, we consider three common stereoscopic artifacts: color mismatch, sharpness mismatch, and geometric distortion. This paper introduces two neural-network-based methods for simultaneous color- and sharpness-mismatch estimation, as well as for estimating geometric distortions. To train these networks we prepared large datasets based on frames from full-length stereoscopic movies and compared the results with methods that previously served in analyses of full-length stereoscopic movies. We used our proposed methods to analyze 100 videos in VR180 format-a new format for stereoscopic videos in virtual reality (VR). This work presents overall results for these videos along with several examples of detected problems.
- Добавил в систему: Лаврушкин Сергей Валерьевич
Прикрепленные файлы
| № | Имя | Описание | Имя файла | Размер | Добавлен |
|---|---|---|---|---|---|
| 1. | Полный текст | _IC3D_2020__Neural_network_based_detection_methods_for_colo… | 6,7 МБ | 28 апреля 2021 [serg_lav] |