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
SpatialTrackerV2: 3D Point Tracking Made EasyCode4
Integrated Switched Capacitor Array and Synchronous Charge Extraction with Adaptive Hybrid MPPT for Piezoelectric Harvesters—0
CharaConsist: Fine-Grained Consistent Character GenerationCode2
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second—0
Learning to Track Any Points from Human Motion—0
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations—0
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelCode1
You Are Your Best Teacher: Semi-Supervised Surgical Point Tracking with Cycle-Consistent Self-Distillation—0
TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion—0
Seurat: From Moving Points to DepthCode2
TAPIP3D: Tracking Any Point in Persistent 3D GeometryCode3
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World—0
TAPNext: Tracking Any Point (TAP) as Next Token PredictionCode0
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D ReconstructionCode2
Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) ChallengeCode0
Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision—0
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better—0
Toward Scalable, Flexible Scene Flow for Point Clouds—0
GIFT: Generated Indoor video frames for Texture-less point tracking—0
VGGT: Visual Geometry Grounded TransformerCode11
Low Complexity Point Tracking of the Myocardium in 2D EchocardiographyCode1
Online Dense Point Tracking with Streaming MemoryCode1
A Training-Free Framework for Precise Mobile Manipulation of Small Everyday Objects—0
Pre-training Auto-regressive Robotic Models with 4D Representations—0
Control Barrier Function-Based Quadratic Programming for SafeOperation of Tethered UAVs—0
Track-On: Transformer-based Online Point Tracking with MemoryCode2
MATCHA:Towards Matching Anything—0
Exploring Temporally-Aware Features for Point TrackingCode2
ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking—0
GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking—0
MATCHA: Towards Matching AnythingCode2
GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking—0
Dynamic Camera Poses and Where to Find Them—0
Microcontroller-Driven MPPT System for Enhanced Photovoltaic Efficiency: An Experimental Approach in Nepal—0
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation—0
EgoPoints: Advancing Point Tracking for Egocentric Videos—0
Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark—0
TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video—0
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild—0
Agile UAV landing control on moving ship in adverse conditions—0
Object and Contact Point Tracking in Demonstrations Using 3D Gaussian Splatting—0
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events—0
A-MFST: Adaptive Multi-Flow Sparse Tracker for Real-Time Tissue Tracking Under Occlusion—0
CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real VideosCode7
Combing Text-based and Drag-based Editing for Precise and Flexible Image Editing—0
Neural Eulerian Scene Flow Fields—0
Transformer based time series prediction of the maximum power point for solar photovoltaic cells—0
Self-Supervised Any-Point Tracking by Contrastive Random WalksCode2
Foundation Models for Amodal Video Instance Segmentation in Automated DrivingCode0
Tracking Any Point with Frame-Event Fusion Network at High Frame RateCode0
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