Exploring object-centric temporal modeling for efficient multi-view 3d object detection

S Wang, Y Liu, T Wang, Y Li… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …

Language prompt for autonomous driving

D Wu, W Han, T Wang, Y Liu, X Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
A new trend in the computer vision community is to capture objects of interest following
flexible human command represented by a natural language prompt. However, the progress …

Exploring recurrent long-term temporal fusion for multi-view 3d perception

C Han, J Yang, J Sun, Z Ge, R Dong… - IEEE Robotics and …, 2024 - ieeexplore.ieee.org
Long-term temporal fusion is a crucial but often overlooked technique in camera-based
Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner …

Panacea: Panoramic and controllable video generation for autonomous driving

Y Wen, Y Zhao, Y Liu, F Jia, Y Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
The field of autonomous driving increasingly demands high-quality annotated training data.
In this paper we propose Panacea an innovative approach to generate panoramic and …

End-to-end 3d tracking with decoupled queries

Y Li, Z Yu, J Philion, A Anandkumar… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this work, we present an end-to-end framework for camera-based 3D multi-object tracking,
called DQTrack. To avoid heuristic design in detection-based trackers, recent query-based …

Query-based temporal fusion with explicit motion for 3d object detection

J Hou, Z Liu, Z Zou, X Ye, X Bai - Advances in Neural …, 2024 - proceedings.neurips.cc
Effectively utilizing temporal information to improve 3D detection performance is vital for
autonomous driving vehicles. Existing methods either conduct temporal fusion based on the …

QUEST: Query stream for practical cooperative perception

S Fan, H Yu, W Yang, J Yuan… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Cooperative perception can effectively enhance individual perception performance by
providing additional viewpoint and expanding the sensing field. Existing cooperation …

Motiontrack: end-to-end transformer-based multi-object tracking with lidar-camera fusion

C Zhang, C Zhang, Y Guo, L Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Multiple Object Tracking (MOT) is crucial to autonomous vehicle perception. End-to-
end transformer-based algorithms, which detect and track objects simultaneously, show …

Quest: Query stream for vehicle-infrastructure cooperative perception

S Fan, H Yu, W Yang, J Yuan, Z Nie - arxiv preprint arxiv:2308.01804, 2023 - arxiv.org
Cooperative perception can effectively enhance individual perception performance by
providing additional viewpoint and expanding the sensing field. Existing cooperation …

Trajectoryformer: 3d object tracking transformer with predictive trajectory hypotheses

X Chen, S Shi, C Zhang, B Zhu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract 3D multi-object tracking (MOT) is vital for many applications including autonomous
driving vehicles and service robots. With the commonly used tracking-by-detection …