AI Paper Atlas

Research map / 3D vision / Human pose estimation

OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields

Zhe Cao, Gines Hidalgo, Tomas Simon, Shih-En Wei, Yaser Ajmal Sheikh

TPAMI 2019 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 6,288 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use PAF-based parsing instead of one-midpoint representation (ablation)OpenPose · MPII validation (PCKh-0.5)mAP: 2.9% higher than one-midpoint and 2.3% higher than two intermediate pointsImproved
add masks of unlabeled persons to the training loss (ablation)OpenPose · MPII validationmAP: further improves the performance by 2.3%Improved
use minimal tree edges (13) instead of fully connected graph (91 edges) with greedy parsing (ablation)OpenPose · MPII custom validationmAP: 78.3 -> 77.4 (362 s -> 0.005 s per image)No clear effect
train the network only on tree edges (separate training) (ablation)OpenPose greedy tree · MPII custom validationmAP: 77.4 -> 79.1Improved
add 3-scale search to inference (ablation)OpenPose · MPII full test setmAP: 72.5 -> 75.6Improved
add single-person CPM refinement to bottom-up output (ablation)OpenPose original · COCO validationAP: 58.4 -> 61.0Improved
replace SSD detector with ground-truth boxes in top-down CPM (ablation)top-down CPM · COCO validationAP: 52.7 -> 62.7Improved
predict PAFs first as prior for confidence maps instead of confidence maps first (ablation)OpenPose 6-stage · COCO validationAP: 61.0 -> 65.3Improved
allocate more stages to PAF branch (5 PAF - 1 CM vs 3 PAF - 3 CM) (ablation)OpenPose 6-stage · COCO validationAP: 65.0 -> 65.3Improved
reduce to 3 PAF - 1 CM (4 stages) (ablation)OpenPose · COCO validationAP: 65.3 -> 64.6Mixed
add foot keypoints to training (body+foot vs body-only) (ablation)OpenPose · COCO validationAP: 65.2 -> 65.3No clear effect
use new body+foot architecture on GPU instead of original modelOpenPose · runtime, CUDAinference time: 73 ms -> 36 msImproved

Later papers that compared with this method

10 later accepted papers report OpenPose as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

2 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy