BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 1477-1485
DOI: 10.1609/aaai.v37i2.25233 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Yinhao Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 799-mal zitiert (Crossref).
Abstract (Originalsprache)
In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View~(BEV) 3D object detection. Our work is based on a key observation -- depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%. Codes have been released.
Zitieren
APA
Li, Y., Ge, Z., Yu, G., Yang, J., Wang, Z., Shi, Y., Sun, J., & Li, Z. (2023). BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 1477-1485. https://doi.org/10.1609/aaai.v37i2.25233
Vancouver
Li Y, Ge Z, Yu G, Yang J, Wang Z, Shi Y, et al. BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):1477-1485. doi:10.1609/aaai.v37i2.25233
BibTeX
@article{Li2023,
author = {Li, Yinhao and Ge, Zheng and Yu, Guanyi and Yang, Jinrong and Wang, Zengran and Shi, Yukang and Sun, Jianjian and Li, Zeming},
title = {BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {2},
pages = {1477--1485},
doi = {10.1609/aaai.v37i2.25233}
}
EUVIMED