Project AURIONAI Use-Cases Research & Innovation
Google
vision

BlazePose GHUM

On-device body pose tracking with 33 landmarks, from the paper "BlazePose".

GoogleGoogleUSAMediaPipe vision modelsFamily
Example pose landmarks drawn as a wireframe over a person in a meditative pose, from Google's MediaPipe pose landmarker guide.
Levelvariant
Classvision
Parametersnot in the notes
Contextnot in the notes
Released17 Jun 2020
Opennessopen weights permissive
Runs onmobile or NPU
Statusactive

R&D Topics

Human pose estimationexemplarEfficient vision networks for mobile and edge devicesproduced by

Identity

Developer
Google
Family
MediaPipe vision models
Released
17 Jun 2020 sourcesannouncement page
Weights published
25 Feb 2024
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
Lite, Full and Heavy; 33 landmarks.
Context length
not in the notes
Input
image
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
Edge or toolkit builds listed in: MediaPipe.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2006.10204 https://arxiv.org/abs/2006.10204
  2. huggingface.co/qualcomm/MediaPipe-Pose-Estimation https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation
  3. huggingface.co/api/models?pipeline_tag=keypoint-detection&so... https://huggingface.co/api/models?pipeline_tag=keypoint-detection&sort=downloads&limit=50
  4. ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker https://ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BlazePose GHUM", https://aurion.semai.id/models/google-blazepose/, records of October 2026.