SOTAVerified

Point Tracking

Point Tracking, often referred to as Tracking any Point (TAP) involves acquiring, focusing on, and continuously tracking specific target point/points across video frames. The system identifies the target point, maintains focus, and predicts its movement, enabling smooth tracking even if the target moves unpredictably, or through occlusions. TAP has wide applications like object tracking, surveillance, and autonomous navigation.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 151 papers

TitleStatusHype
VGGT: Visual Geometry Grounded TransformerCode11
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image ManifoldCode7
CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real VideosCode7
VGGSfM: Visual Geometry Grounded Deep Structure From MotionCode5
BootsTAP: Bootstrapped Training for Tracking-Any-PointCode5
TAPVid-3D: A Benchmark for Tracking Any Point in 3DCode5
CoTracker: It is Better to Track TogetherCode4
FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient DescentCode4
SpatialTrackerV2: 3D Point Tracking Made EasyCode4
Visual Geometry Grounded Deep Structure From MotionCode3
TAPIR: Tracking Any Point with per-frame Initialization and temporal RefinementCode3
TAPIP3D: Tracking Any Point in Persistent 3D GeometryCode3
TAP-Vid: A Benchmark for Tracking Any Point in a VideoCode3
Local All-Pair Correspondence for Point TrackingCode3
LEAP-VO: Long-term Effective Any Point Tracking for Visual OdometryCode3
Segment Anything Meets Point TrackingCode3
EchoTracker: Advancing Myocardial Point Tracking in EchocardiographyCode2
CharaConsist: Fine-Grained Consistent Character GenerationCode2
Track-On: Transformer-based Online Point Tracking with MemoryCode2
FreeDrag: Feature Dragging for Reliable Point-based Image EditingCode2
Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular VideosCode2
Self-Supervised Any-Point Tracking by Contrastive Random WalksCode2
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D ReconstructionCode2
Dense Optical Tracking: Connecting the DotsCode2
Exploring Temporally-Aware Features for Point TrackingCode2
Perception Test: A Diagnostic Benchmark for Multimodal Video ModelsCode2
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in VideosCode2
Decomposition Betters Tracking Everything EverywhereCode2
Seurat: From Moving Points to DepthCode2
PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point TrackingCode2
MATCHA: Towards Matching AnythingCode2
Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment AnythingCode1
SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal ScenesCode1
PTTR: Relational 3D Point Cloud Object Tracking with TransformerCode1
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud VideosCode1
Online Dense Point Tracking with Streaming MemoryCode1
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelCode1
Low Complexity Point Tracking of the Myocardium in 2D EchocardiographyCode1
MFT: Long-Term Tracking of Every PixelCode1
Deep Learning based Virtual Point Tracking for Real-Time Target-less Dynamic Displacement Measurement in Railway ApplicationsCode1
Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with TransformerCode1
Motion-prior Contrast Maximization for Dense Continuous-Time Motion EstimationCode1
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild—0
Data-driven predictive control with improved performance using segmented trajectories—0
Analysis, design, and implementation of the AFZ converter applied to photovoltaic systems—0
A Unified Power-Setpoint Tracking Algorithm for Utility-Scale PV Systems with Power Reserves and Fast Frequency Response Capabilities—0
Adaptive maximum power point tracking using neural networks for a photovoltaic systems according grid—0
Control Barrier Function-Based Quadratic Programming for SafeOperation of Tethered UAVs—0
Context-PIPs: Persistent Independent Particles Demands Spatial Context Features—0
Analysis and implementation of the Buck-Boost Modified Series Forward converter applied to photovoltaic systems—0
Show:102550
← PrevPage 1 of 4Next →
All datasetsTAP-Vid-DAVISPointOdysseyTAP-Vid-DAVIS-FirstTAP-Vid-KineticsTAP-Vid-Kinetics-FirstTAP-Vid-RGB-StackingPerception TestTAP-Vid

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LocoTrack-BAverage Jaccard69.4—Unverified
2BootsTAPIRAverage Jaccard66.2—Unverified
3CoTrackerAverage Jaccard65.9—Unverified
#ModelMetricClaimedVerifiedStatus
1PIPs++Survival50.47—Unverified
2PIPs+Survival49.88—Unverified
#ModelMetricClaimedVerifiedStatus
1LocoTrack-BAverage Jaccard64.8—Unverified
2CoTrackerAverage Jaccard62.2—Unverified
#ModelMetricClaimedVerifiedStatus
1BootsTAPIRAverage Jaccard61.4—Unverified
2LocoTrack-BAverage Jaccard59.1—Unverified
#ModelMetricClaimedVerifiedStatus
1LocoTrack-BAverage Jaccard52.3—Unverified
2CoTrackerAverage Jaccard48.8—Unverified
#ModelMetricClaimedVerifiedStatus
1BootsTAPIRAverage Jaccard72.4—Unverified
2LocoTrack-BAverage Jaccard70.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Static BaselineAverage Jaccard0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1PIPs++MTE4.6—Unverified