| Real-World Point Tracking with Verifier-Guided Pseudo-Labeling | ✓ Link | 0.709 | 0.94 | 0.826 | Track-On-R (extra data) | 2026-03-12 |
| BootsTAP: Bootstrapped Training for Tracking-Any-Point | ✓ Link | 0.692 | 0.895 | 0.813 | BootsTAPIR (extra data) | 2024-02-01 |
| Track-On2: Enhancing Online Point Tracking with Memory | ✓ Link | 0.681 | 0.934 | 0.805 | Track-On2 (DINOv3) | 2025-09-23 |
| Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking | ✓ Link | 0.665 | 0.9 | 0.787 | DiTracker (CoTracker3) (extra data) | 2025-12-23 |
| CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos | ✓ Link | 0.664 | 0.908 | 0.788 | CoTracker3 Online (Kub+15k) (extra data) | 2024-10-15 |
| AnthroTAP: Learning Point Tracking with Real-World Motion | | 0.647 | 0.884 | 0.792 | Anthro-LocoTrack (extra data) | 2025-07-08 |
| TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video | ✓ Link | 0.645 | 0.897 | 0.773 | TAPTRv3 (online, ResNet-18) | 2024-11-27 |
| Track-On: Transformer-based Online Point Tracking with Memory | ✓ Link | 0.635 | 0.894 | 0.764 | Track-On | 2025-01-30 |
| Local All-Pair Correspondence for Point Tracking | ✓ Link | 0.625 | 0.87 | 0.76 | LocoTrack-S (extra data) | 2024-07-22 |
| TAPNext++: What's Next for Tracking Any Point (TAP)? | ✓ Link | 0.611 | 0.896 | 0.752 | TAPNext++ (extra data) | 2026-04-12 |
| Online Dense Point Tracking with Streaming Memory | ✓ Link | 0.607 | 0.875 | 0.736 | SPOT | 2025-03-09 |