BlazePose: On-device Real-time Body Pose tracking

Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Zhu, Fan Zhang +1 more
6/17/2020
cs.CV

Official code: google-ai-edge/mediapipe (37,344 stars, Apache-2.0, last commit 2026-10-20).

Abstract

We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates.

View on arXivView PDF

Code Implementations(1)

google-ai-edge/mediapipeOfficial100%
Apache-2.0

Cross-platform, customizable ML solutions for live and streaming media.

37,3446,189C, C++Jun 13, 20194 days agoApache-2.0
androidaudio-processingc-plus-pluscalculatorcomputer-vision+12 more

Similar Papers

DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones

89% match2024

MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices

89% match2023

MobilePoser: Real-Time Full-Body Pose Estimation and 3D Human Translation from IMUs in Mobile Consumer Devices

86% match1 repo1442025

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

83% match1 repo502023

Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile

82% match2023

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

82% match2 repos922021

Cite this paper

@article{bazarevsky2020blazepose,
  title  = {BlazePose: On-device Real-time Body Pose tracking},
  author = {Valentin Bazarevsky and Ivan Grishchenko and Karthik Raveendran and Tyler Zhu and Fan Zhang and Matthias Grundmann},
  year   = {2020},
  eprint = {2006.10204},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2006.10204}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2006.10204.svg)](https://codeofpaper.com/paper/2006.10204)

Discussion