Источник
ISMAR
Дата публикации
03.11.2021
Авторы
Илья Макаров
Глеб Борисенко
Поделиться
Depth Inpainting via Vision Transformer
Human-centered computing,
Human computer interaction (HCI),
Interaction paradigms,
Mixed / augmented reality,
Computing methodologies,
Computer vision,
Reconstruction, 3D imaging,
Computational photograph
Аннотация
Depth inpainting is a crucial task for working with augmented reality. In previous works missing depth values are completed by convolutional encoder-decoder networks, which is a kind of bottleneck. But nowadays vision transformers showed very good quality in various tasks of computer vision and some of them became state of the art. In this study, we presented a supervised method for depth inpainting by RGB images and sparse depth maps via vision transformers. The proposed model was trained and evaluated on the NYUv2 dataset. Experiments showed that a vision transformer with a restrictive convolutional tokenization model can improve the quality of the inpainted depth map.
Похожие публикации
Вы можете задать нам вопрос или предложить совместный проект в области ИИ
partner@airi.net
По вопросам научного
сотрудничества и партнерства
сотрудничества и партнерства
pr@airi.net
Для журналистов и СМИ