google-deepmind/tapnet

Tracking Any Point (TAP)

59
/ 100
Established

This project helps you accurately track specific points or objects through video footage, even if they move, are temporarily hidden, or change appearance. You input a video and select a point, and it outputs the exact path (trajectory) of that point across all frames. It's ideal for robotics engineers, motion analysts, or researchers studying object movement.

1,814 stars. Actively maintained with 3 commits in the last 30 days.

Use this if you need precise, long-term tracking of individual points or features within complex videos, including scenarios with occlusions or re-detections.

Not ideal if you only need general object detection or classification rather than detailed point-level trajectory analysis.

robotics motion-analysis video-analytics computer-vision behavioral-science
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,814

Forks

176

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jan 22, 2026

Commits (30d)

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/google-deepmind/tapnet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.