Fully Sparse Fusion for 3D Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-11 · 46 (11) · 7217-7231
DOI: 10.1109/tpami.2024.3392303 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-11. Verfasst von Yingyan Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, 2035 Innovation Program of CAS.
Abstract (Originalsprache)
Currently prevalent multi-modal 3D detection methods rely on dense detectors that usually use dense Bird's-Eye-View (BEV) feature maps. However, the cost of such BEV feature maps is quadratic to the detection range, making it not scalable for long-range detection. Recently, LiDAR-only fully sparse architecture has been gaining attention for its high efficiency in long-range perception. In this paper, we study how to develop a multi-modal fully sparse detector. Specifically, our proposed detector integrates the well-studied 2D instance segmentation into the LiDAR side, which is parallel to the 3D instance segmentation part in the LiDAR-only baseline. The proposed instance-based fusion framework maintains full sparsity while overcoming the constraints associated with the LiDAR-only fully sparse detector. Our framework showcases state-of-the-art performance on the widely used nuScenes dataset, Waymo Open Dataset, and the long-range Argoverse 2 dataset. Notably, the inference speed of our proposed method under the long-range perception setting is 2.7× faster than that of other state-of-the-art multimodal 3D detection methods.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- 2035 Innovation Program of CAS
Zitieren
APA
Li, Y., Fan, L., Liu, Y., Huang, Z., Chen, Y., Wang, N., & Zhang, Z. (2024). Fully Sparse Fusion for 3D Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(11), 7217-7231. https://doi.org/10.1109/tpami.2024.3392303
Vancouver
Li Y, Fan L, Liu Y, Huang Z, Chen Y, Wang N, et al. Fully Sparse Fusion for 3D Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(11):7217-7231. doi:10.1109/tpami.2024.3392303
BibTeX
@article{Li2024,
author = {Li, Yingyan and Fan, Lue and Liu, Yang and Huang, Zehao and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang},
title = {Fully Sparse Fusion for 3D Object Detection},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {11},
pages = {7217--7231},
doi = {10.1109/tpami.2024.3392303}
}
EUVIMED