# BlazePose: On-device Real-time Body Pose tracking

arXiv: https://arxiv.org/abs/2006.10204 · HTML: https://mlsanity.com/paper/2006.10204/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 30 of 113)

- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [Generative Neural Articulated Radiance Fields](https://mlsanity.com/paper/2206.14314/) (2022)
- [HSPACE: Synthetic Parametric Humans Animated in Complex Environments](https://mlsanity.com/paper/2112.12867/) (2021)
- [EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams](https://mlsanity.com/paper/2404.08640/) (2024)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality](https://mlsanity.com/paper/2112.05892/) (2021)
- [PoseRAC: Pose Saliency Transformer for Repetitive Action Counting](https://mlsanity.com/paper/2303.08450/) (2023)
- [BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation](https://mlsanity.com/paper/2206.11678/) (2022)
- [Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues](https://mlsanity.com/paper/2401.02746/) (2024)
- [Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection](https://mlsanity.com/paper/2305.01652/) (2023)
- [Biometrics and Behavior Analysis for Detecting Distractions in e-Learning](https://mlsanity.com/paper/2405.15434/) (2024)
- [MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation](https://mlsanity.com/paper/2605.20183/) (2026)
- [Towards Single Camera Human 3D-Kinematics](https://mlsanity.com/paper/2301.05435/) (2023)
- [On-device Real-time Hand Gesture Recognition](https://mlsanity.com/paper/2111.00038/) (2021)
- [HumMUSS: Human Motion Understanding using State Space Models](https://mlsanity.com/paper/2404.10880/) (2024)
- [Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods](https://mlsanity.com/paper/2406.17382/) (2024)
- [Full-Body Cardiovascular Sensing with Remote Photoplethysmography](https://mlsanity.com/paper/2303.09638/) (2023)
- [Towards the extraction of robust sign embeddings for low resource sign language recognition](https://mlsanity.com/paper/2306.17558/) (2023)
- [VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG](https://mlsanity.com/paper/2311.14775/) (2023)
- [The AffectToolbox: Affect Analysis for Everyone](https://mlsanity.com/paper/2402.15195/) (2024)
- [Design2Cloth: 3D Cloth Generation from 2D Masks](https://mlsanity.com/paper/2404.02686/) (2024)
- [WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users](https://mlsanity.com/paper/2404.17063/) (2024)
- [Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors](https://mlsanity.com/paper/2405.03545/) (2024)
- [A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body Movement Analysis](https://mlsanity.com/paper/2407.00521/) (2024)
- [WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Users](https://mlsanity.com/paper/2409.08494/) (2024)
- [Using Learnable Physics for Real-Time Exercise Form Recommendations](https://mlsanity.com/paper/2310.07221/) (2023)
- [Clothes-Changing Person Re-identification Based On Skeleton Dynamics](https://mlsanity.com/paper/2503.10759/) (2025)
- [EMERSK -- Explainable Multimodal Emotion Recognition with Situational Knowledge](https://mlsanity.com/paper/2306.08657/) (2023)
- [Selecting the motion ground truth for loose-fitting wearables: benchmarking optical MoCap methods](https://mlsanity.com/paper/2307.11881/) (2023)
- [3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding](https://mlsanity.com/paper/2310.10131/) (2023)

## Abstract (arXiv)

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.