OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields
Open accessThe DOI matches its Crossref record, with a small difference in title or year; 78 of the 78 references it cites were found in a registry or an index.
Abstract
Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of OpenPose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“OpenPose can detect people in a frame and generate a skeleton of body parts for each person detected.”
From Opportunity++: A Multimodal Dataset for Video- and Wearable, Object and Ambient Sensors-Based Human Activity Recognition (2021) · cites this paper as Cao et al. (2021)
The cited source says what the claim attributes to it.
In the citing paper
“However, in order to make the videos interesting for researchers, we also provide the pose tracking of all the people in the scene generated with OpenPose (Cao et al. (2021)).”
From Opportunity++: A Multimodal Dataset for Video- and Wearable, Object and Ambient Sensors-Based Human Activity Recognition (2021) · cites this paper as Cao et al. (2021)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
(2016) · Cited by 31,590
An Algorithm for Least-Squares Estimation of Nonlinear Parameters
Marquardt, D. W. (1963) · Journal of the Society for Industrial and Applied Mathematics · doi:10.1137/0111030 · Cited by 30,728
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · cited 3×
“If we use the state-of-the-art object detector, Single Shot MultiBox Detector (SSD) [74], the performance drops 10%.”
BackgroundMethod
Research works printed but not linked: 1
- [5] K. He, G. Gkioxari, P. Doll´ ar, and R. Girshick, 'Mask r-cnn,' in ICCV , 2017. -
Cited by
Items 1,001–1,017 of 1,017
VideoDex: Learning dexterity from internet videos
Shaw, K., Bahl, S., & Pathak, D. (2022) · arXiv · doi:10.48550/arxiv.2212.04498 · Cited by 23
The fundamentals of eye tracking part 6: working with areas of interest
Hooge, I. T. C., Nyström, M., Niehorster, D. C., Andersson, R., Foulsham, T., Nuthmann, A., & Hessels, R. S. (2026) · Behavior Research Methods · doi:10.3758/s13428-025-02937-3 · Cited by 22
Toma, C., Popa, M., Iancu, B., Doinea, M., Pascu, A., & Ioan-Dutescu, F. (2022) · Electronics · doi:10.3390/electronics11213507 · Cited by 22
Fighting deepfakes using body language analysis
Yasrab, R., Jiang, W., & Riaz, A. (2021) · Forecasting · doi:10.3390/forecast3020020 · Cited by 20
(2021) · doi:10.1145/3450268.3453521 · Cited by 19
Mujirishvili, T., Fedosov, A., Hashemifard, K., Climent-Pérez, P., & Florez-Revuelta, F. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642164 · Cited by 18
“It was not until the advent of ‘deep learning ’-based methods for human pose estimation [11, 37] that this was made possible.”
BackgroundFortes Rey, V., Garewal, K. K., & Lukowicz, P. (2021) · Applied Sciences · doi:10.3390/app11073094 · Cited by 17
“Obtaining 3D poses is possible with a calibrated system of more than one camera [21].”
BackgroundMethodInfluentialAhmad, S., Morerio, P., & Del Bue, A. (2024) · IEEE Access · doi:10.1109/access.2024.3399539 · Cited by 16
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Jocher, G., Qiu, J., Liu, M., Lyu, S., Akyon, F. C., & Kalfaoglu, M. E. (2026) · arXiv · doi:10.48550/arxiv.2606.03748 · Cited by 16
“HRNet maintains high-resolution representations through parallel subnetwork fusion [64], while OpenPose takes a bottom-up approach by jointly predicting keypoints and Part Affinity Fields [4].”
An Infrared Thermography Model Enabling Remote Body Temperature Screening Up to 10 Meters
Chin, J. W., Long Wong, K., Chan, T. T., Suhartono, K., & So, R. H. Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00429 · Cited by 16
I Find Your Lack of Uncertainty in Computer Vision Disturbing
Valdenegro-Toro, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00139 · Cited by 15
SignLLM: Sign Language Production Large Language Models
Fang, S., Chen, C., Wang, L., Zheng, C., Sui, C., & Tian, Y. (2025) · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00690 · Cited by 15
Person Re-ID by Fusion of Video Silhouettes and Wearable Signals for Home Monitoring Applications
Masullo, A., Burghardt, T., Damen, D., Perrett, T., & Mirmehdi, M. (2020) · Sensors · doi:10.3390/s20092576 · Cited by 10
Recognizing American Sign Language Nonmanual Signal Grammar Errors in Continuous Videos
Vahdani, E., Jing, L., Tian, Y., & Huenerfauth, M. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9413126 · Cited by 7
Zobi, M., Bolzani, L., Tabii, Y., & Oulad Haj Thami, R. (2025) · Sensors · doi:10.3390/s25216783 · Cited by 6
A Multi-Agent Digital Twin Framework for AI-Driven Fitness Coaching
Vahdati, M. (., Gholizadeh HamlAbadi, K., Laamarti, F., & El Saddik, A. (2025) · Proceedings of the 2025 ACM International Conference on Interactive Media Experiences · doi:10.1145/3706370.3731651 · Cited by 5
Domain-Adaptive Online Active Learning for Real-Time Intelligent Video Analytics on Edge Devices
Boldo, M., De Marchi, M., Martini, E., Aldegheri, S., & Bombieri, N. (2024) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2024.3453188 · Cited by 4
“It employs CNNs and platforms, such as TRTPose [13] and OpenPose [14].”
Method
Metadata
- Authors
- Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., & Sheikh, Y.
- Affiliations
- University of California, Berkeley (US)
- Carnegie Mellon University (US)
- Meta (United States) (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2021-01-01
- Volume
- 43
- Issue
- 1
- Pages
- 172-186
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W2962730651
- Cited by
- 5,536
- References
- 77
- Citations by year
- 2026: 608 · 2025: 777 · 2024: 752 · 2023: 882 · 2022: 918 · 2021: 965
- FWCI
- 280.23
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Intelligence Advanced Research Projects Activity
- Department of Interior / Interior Business Center (D17PC00340)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- part affinity fields, real-time pose detection, bottom-up pose estimation, hand keypoint detection, facial keypoint detection, inference latency reduction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.