|
ИСТИНА |
Войти в систему Регистрация |
Интеллектуальная Система Тематического Исследования НАукометрических данных |
||
ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectionстатья
- Авторы: Rukhovich Danila, Vorontsova Anna, Konushin Anton
- Сборник: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
- Год издания: 2022
- Место издания: IEEE
- Первая страница: 2397
- Последняя страница: 2406
- DOI: 10.1109/wacv51458.2022.00133
- Аннотация: In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxel-Net, a novel fully convolutional method of 3D object detection based on posed monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection on KITTI (monocular) and nuScenes (multi-view) benchmarks among all methods that accept RGB images. Moreover, it surpasses existing RGB-based 3D object detection methods on the SUN RGB-D dataset. On ScanNet, ImVoxelNet sets a new benchmark for multi-view 3D object detection. The source code and the trained models are available at https://github.com/saic-vul/imvoxelnet.
- Добавил в систему: Конушин Антон Сергеевич