SOTAVerified

3D Object Tracking

3D Object Tracking is a computer vision task dedicated to monitoring and precisely locating objects as they navigate within a three-dimensional environment. It frequently utilizes 3D object detection techniques to pinpoint the objects and establish unique identifications that persist across multiple frames.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 67 papers

TitleStatusHype
DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking—0
Self-Supervised Pre-training with Combined Datasets for 3D Perception in Autonomous Driving—0
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction—0
TrackOcc: Camera-based 4D Panoptic Occupancy TrackingCode2
A Modular Pipeline for 3D Object Tracking Using RGB CamerasCode0
Prior-free 3D Object TrackingCode1
Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection—0
GSOT3D: Towards Generic 3D Single Object Tracking in the WildCode0
Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack—0
Panacea+: Panoramic and Controllable Video Generation for Autonomous DrivingCode3
SiamMo: Siamese Motion-Centric 3D Object TrackingCode0
DGD: Dynamic 3D Gaussians Distillation—0
SceneTracker: Long-term Scene Flow Estimation NetworkCode2
RCooper: A Real-world Large-scale Dataset for Roadside Cooperative PerceptionCode2
GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly GuidanceCode1
Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object TrackingCode0
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel ObjectsCode4
CenterRadarNet: Joint 3D Object Detection and Tracking Framework using 4D FMCW Radar—0
Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile DatasetCode1
The Interstate-24 3D Dataset: a new benchmark for 3D multi-camera vehicle tracking—0
Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking—0
Delving into Motion-Aware Matching for Monocular 3D Object TrackingCode1
BOTT: Box Only Transformer Tracker for 3D Object Tracking—0
S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations—0
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory HypothesesCode1
Show:102550
← PrevPage 1 of 3Next →
All datasetsArgoverse CVPR 2020RTB

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Benson-RAVG-RANK99,999—Unverified
2pyDort_v1_rnet18_cv_cv_pedestrian_incAVG-RANK99,999—Unverified
3kevinsagen47AVG-RANK99,999—Unverified
4test_1AVG-RANK99,999—Unverified
5yk_yuanAVG-RANK99,999—Unverified
6maxage15-minhits5-conf0.3-thr0.01AVG-RANK99,999—Unverified
7kitty cov id = 1AVG-RANK99,999—Unverified
8EdwardAVG-RANK99,999—Unverified
9submit1AVG-RANK99,999—Unverified
10submit02AVG-RANK99,999—Unverified
#ModelMetricClaimedVerifiedStatus
1Mb-ICGADDS AUC91.1—Unverified