# Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

arXiv: https://arxiv.org/abs/1811.12004 · HTML: https://mlsanity.com/paper/1811.12004/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

## Built on by (most cited first, 30 of 42)

- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose](https://mlsanity.com/paper/2111.12696/) (2021)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation](https://mlsanity.com/paper/2205.01271/) (2022)
- [Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes](https://mlsanity.com/paper/2403.18546/) (2024)
- [PresSim: An End-to-end Framework for Dynamic Ground Pressure Profile Generation from Monocular Videos Using Physics-based 3D Simulation](https://mlsanity.com/paper/2302.00391/) (2023)
- [Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers](https://mlsanity.com/paper/2210.00507/) (2022)
- [GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation](https://mlsanity.com/paper/2407.10756/) (2024)
- [Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices](https://mlsanity.com/paper/2106.15304/) (2021)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG](https://mlsanity.com/paper/2311.14775/) (2023)
- [Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoring](https://mlsanity.com/paper/2205.01515/) (2022)
- [Occupancy Planes for Single-view RGB-D Human Reconstruction](https://mlsanity.com/paper/2208.02817/) (2022)
- [DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones](https://mlsanity.com/paper/2407.13777/) (2024)
- [Your Turn: At Home Turning Angle Estimation for Parkinson's Disease Severity Assessment](https://mlsanity.com/paper/2408.08182/) (2024)
- [Towards Automated and Marker-less Parkinson Disease Assessment: Predicting UPDRS Scores using Sit-stand videos](https://mlsanity.com/paper/2104.04650/) (2021)
- [ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones](https://mlsanity.com/paper/2108.10515/) (2021)
- [ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation](https://mlsanity.com/paper/2202.00753/) (2022)
- [Binarizing by Classification: Is soft function really necessary?](https://mlsanity.com/paper/2205.07433/) (2022)
- [Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot](https://mlsanity.com/paper/2311.05334/) (2023)
- [Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation](https://mlsanity.com/paper/2104.10414/) (2021)
- [MotionInput v2.0 supporting DirectX: A modular library of open-source gesture-based machine learning and computer vision methods for interacting and controlling existing software with a webcam](https://mlsanity.com/paper/2108.04357/) (2021)
- [A Review on Human Pose Estimation](https://mlsanity.com/paper/2110.06877/) (2021)
- [DF-Captcha: A Deepfake Captcha for Preventing Fake Calls](https://mlsanity.com/paper/2208.08524/) (2022)
- [MARIO: Modular and Extensible Architecture for Computing Visual Statistics in RoboCup SPL](https://mlsanity.com/paper/2209.09987/) (2022)
- [A Video-based Detector for Suspicious Activity in Examination with OpenPose](https://mlsanity.com/paper/2307.11413/) (2023)
- [A webcam-based machine learning approach for three-dimensional range of motion evaluation](https://mlsanity.com/paper/2310.07322/) (2023)

## Abstract (arXiv)

In this work we adapt multi-person pose estimation architecture to use it on edge devices. We follow the bottom-up approach from OpenPose, the winner of COCO 2016 Keypoints Challenge, because of its decent quality and robustness to number of people inside the frame. With proposed network design and optimized post-processing code the full solution runs at 28 frames per second (fps) on IntelunicodexAE NUC 6i7KYB mini PC and 26 fps on CoreTM i7-6850K CPU. The network model has 4.1M parameters and 9 billions floating-point operations (GFLOPs) complexity, which is just ~15% of the baseline 2-stage OpenPose with almost the same quality. The code and model are available as a part of IntelunicodexAE OpenVINOTM Toolkit.