3D Multi-Object Tracking
31 papers with code • 6 benchmarks • 7 datasets
Image: Weng et al
Benchmarks
These leaderboards are used to track progress in 3D Multi-Object Tracking
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
KITTI
nuScenes
Waymo Open Dataset
nuScenes LiDAR only
MOTFront
3D-ZeF
CVB
Most implemented papers
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects.
3D Multi-Object Tracking Based on Uncertainty-Guided Data Association
In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage.
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
exiawsh/streampetr
•
•
ICCV 2023
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.
CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception
Autonomous driving requires an accurate and fast 3D perception system that includes 3D object detection, tracking, and segmentation.
You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance.
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots.
3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking
dsx0511/3dmotformer
•
•
ICCV 2023
Tracking 3D objects accurately and consistently is crucial for autonomous vehicles, enabling more reliable downstream tasks such as trajectory prediction and motion planning.
Delving into Motion-Aware Matching for Monocular 3D Object Tracking
kuanchihhuang/moma-m3t
•
•
ICCV 2023
In this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches.
Offline Tracking with Object Permanence
tudelft-iv-students/offline-tracking-with-object-permanence
•
•
In this work, we propose an offline tracking model that focuses on occluded object tracks.
Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception
phi-wol/hydra
•
•
Low-cost, vision-centric 3D perception systems for autonomous driving have made significant progress in recent years, narrowing the gap to expensive LiDAR-based methods.
