SOTAVerified

3D Single Object Tracking

3D tracking of a single object, based on an initial 3D bounding box, provided to the tracker. 3D single object tracking is commonly performed using point cloud data from Lidars, as it provides valuable depth information, which is lost in camera images. However, irregular point cloud structure and an increasing point sparsity with distance makes Lidar-based 3D single object tracking a nontrivial task.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–43 of 43 papers

TitleStatusHype
Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point CloudsCode2
An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point CloudsCode2
P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point CloudsCode2
VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo ImagesCode2
SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud TrackingCode1
3D Siamese Transformer Network for Single Object Tracking on Point CloudsCode1
A Lightweight and Detector-free 3D Single Object Tracker on Point CloudsCode1
BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye ViewCode1
Box-Aware Feature Enhancement for Single Object Tracking on Point CloudsCode1
GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking LossCode1
GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point CloudsCode1
M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object TrackingCode1
MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle ConsistencyCode1
Motion-to-Matching: A Mixed Paradigm for 3D Single Object TrackingCode1
MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object TrackingCode1
MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual CuesCode1
OSP2B: One-Stage Point-to-Box Network for 3D Siamese TrackingCode1
PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point CloudsCode1
PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point CloudsCode1
Real-time 3D Single Object Tracking with TransformerCode1
Implicit and Efficient Point Cloud Completion for 3D Single Object Tracking—0
MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors—0
Robust 3D Tracking with Quality-Aware Shape Completion—0
Modeling Continuous Motion for 3D Point Cloud Object Tracking—0
Robust Single Object Tracking in LiDAR Point Clouds under Adverse Weather Conditions—0
Correlation Pyramid Network for 3D Single Object Tracking—0
CXTrack: Improving 3D Point Cloud Tracking with Contextual Information—0
FlowTrack: Point-level Flow Network for 3D Single Object Tracking—0
F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Tracking—0
Towards Category Unification of 3D Single Object Tracking on Point Clouds—0
3D Single-object Tracking in Point Clouds with High Temporal Variation—0
Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking—0
Object Preserving Siamese Network for Single Object Tracking on Point Clouds—0
STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking—0
3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud—0
OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds—0
VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking—0
Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object TrackingCode0
SiamMo: Siamese Motion-Centric 3D Object TrackingCode0
Variational Voxel Pseudo Image TrackingCode0
3D-SiamMask: Vision-Based Multi-Rotor Aerial-Vehicle Tracking for a Moving ObjectCode0
Exploiting More Information in Sparse Point Cloud for 3D Single Object TrackingCode0
GSOT3D: Towards Generic 3D Single Object Tracking in the WildCode0
Show:102550

No leaderboard results yet.