Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

Shihao Wang, Yingfei Liu, Tiancai Wang*, Ying Li, Xiangyu Zhang

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

24 引用 (Scopus)

摘要

In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The model is performed in an online manner and the long-term historical information is propagated through object queries frame by frame. Besides, we introduce a motion-aware layer normalization to model the movement of the objects. StreamPETR achieves significant performance improvements only with negligible computation cost, compared to the single-frame baseline. On the standard nuScenes benchmark, it is the first online multi-view method that achieves comparable performance (67.6% NDS & 65.3% AMOTA) with lidar-based methods. The lightweight version realizes 45.0% mAP and 31.7 FPS, outperforming the state-of-the-art method (SOLOFusion) by 2.3% mAP and 1.8× faster FPS. Code has been available at https://github.com/exiawsh/StreamPETR.git.

源语言英语
主期刊名Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
出版商Institute of Electrical and Electronics Engineers Inc.
3598-3608
页数11
ISBN(电子版)9798350307184
DOI
出版状态已出版 - 2023
活动2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, 法国
期限: 2 10月 20236 10月 2023

出版系列

姓名Proceedings of the IEEE International Conference on Computer Vision
ISSN(印刷版)1550-5499

会议

会议2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
国家/地区法国
Paris
时期2/10/236/10/23

指纹

探究 'Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection' 的科研主题。它们共同构成独一无二的指纹。

引用此