Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh
11/24/2016
cs.CV

Official code: ZheC/Realtime_Multi-Person_Pose_Estimation (5,124 stars, last commit 2020-03-21).

Abstract

We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.

View on arXivView PDF

Code Implementations(1)

ZheC/Realtime_Multi-Person_Pose_EstimationOfficial100%

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

5,1241,348Shell, MATLABDec 12, 20166 years agoNOASSERTION
caffecomputer-visioncpp11cvpr-2017deep-learning+5 more

Similar Papers

Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting

84% match1 repo402026

Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle

84% match1 repo2312024

End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer

84% match1 repo252025

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

83% match1 repo4182026

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

83% match1 repo832026

SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Images

83% match2025

Cite this paper

@article{cao2016realtime,
  title  = {Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields},
  author = {Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh},
  year   = {2016},
  eprint = {1611.08050},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1611.08050}
}

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/1611.08050.svg)](https://codeofpaper.com/paper/1611.08050)

Discussion