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

No leaderboard results yet.