Exploring object-centric temporal modeling for efficient multi-view 3d object detection
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 …
multi-view 3D object detection. Built upon the sparse query design in the PETR series, we …
Language prompt for autonomous driving
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 …
flexible human command represented by a natural language prompt. However, the progress …
Exploring recurrent long-term temporal fusion for multi-view 3d perception
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 …
Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner …
Panacea: Panoramic and controllable video generation for autonomous driving
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 …
In this paper we propose Panacea an innovative approach to generate panoramic and …
End-to-end 3d tracking with decoupled queries
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 …
called DQTrack. To avoid heuristic design in detection-based trackers, recent query-based …
Query-based temporal fusion with explicit motion for 3d object detection
Effectively utilizing temporal information to improve 3D detection performance is vital for
autonomous driving vehicles. Existing methods either conduct temporal fusion based on the …
autonomous driving vehicles. Existing methods either conduct temporal fusion based on the …
QUEST: Query stream for practical cooperative perception
Cooperative perception can effectively enhance individual perception performance by
providing additional viewpoint and expanding the sensing field. Existing cooperation …
providing additional viewpoint and expanding the sensing field. Existing cooperation …
Motiontrack: end-to-end transformer-based multi-object tracking with lidar-camera fusion
Abstract Multiple Object Tracking (MOT) is crucial to autonomous vehicle perception. End-to-
end transformer-based algorithms, which detect and track objects simultaneously, show …
end transformer-based algorithms, which detect and track objects simultaneously, show …
Quest: Query stream for vehicle-infrastructure cooperative perception
Cooperative perception can effectively enhance individual perception performance by
providing additional viewpoint and expanding the sensing field. Existing cooperation …
providing additional viewpoint and expanding the sensing field. Existing cooperation …
Trajectoryformer: 3d object tracking transformer with predictive trajectory hypotheses
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 …
driving vehicles and service robots. With the commonly used tracking-by-detection …