# google-deepmind/tapnet

Tracking Any Point (TAP)

Repository: https://github.com/google-deepmind/tapnet
Canonical: https://ross.abutalabs.com/products/tapnet
Homepage: https://deepmind-tapir.github.io/blogpost.html
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: benchmark, point-tracking, robotics, computer-vision, deep-learning
Last push: 2026-07-22T21:53:12+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 35, longevity 99
- inputs: {"age_days": 1399, "days_push": 42, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1968, forks 187 (observed 2026-08-28T04:06:00.632626+00:00)

## What it is
Google DeepMind's official repository for Tracking Any Point (TAP), containing the TAP-Vid and TAPVid-3D benchmarks, the TAPIR and TAPNext point-tracking models, and the RoboTAP robotics extension. It provides models and datasets for tracking arbitrary query points through video sequences.

## Use cases
- track any point through a video
- evaluate point tracking models on TAP-Vid benchmark
- run TAPIR or TAPNext for video point tracking
- use point tracks for robot manipulation imitation learning
- benchmark 3D point tracking on real-world videos
- train point tracking models with bootstrapped video data

## When to choose
- you need state-of-the-art point tracking models like TAPIR or TAPNext
- you want to benchmark point tracking against TAP-Vid or TAPVid-3D
- you're building robotics manipulation systems that rely on point tracks
- you need pretrained checkpoints for video motion analysis

## When to avoid
- you need general object detection or segmentation rather than point tracking
- you want a production-ready application rather than research code
- you can't run GPU-accelerated deep learning models
- you need real-time tracking on edge devices without significant optimization

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, deep-learning, benchmarking
- domain: computer-vision, deep-learning, robotics, machine-learning
- platform: python, cross-platform
- tags: point-tracking, tapir, tapnext, video-understanding, jax, benchmark, robotics, trajectory-estimation, gpu

## Member repositories
- google-deepmind/tapnet (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:00.632626+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:05:11.439251+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/tapnet (fetched 2026-08-28T04:06:00.632626+00:00, sha 41c69f7f9de8)
  - homepage: https://deepmind-tapir.github.io/blogpost.html (fetched 2026-08-29T10:44:45.635693+00:00, sha f73c1c422cd6)
- Data as of 2026-08-30T08:39:29.467469+00:00.