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

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

24 Nov 2016CVPR 2017 7arXiv:1611.08050archive 2025-07-28

Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (ZheC/Realtime_Multi-Person_Pose_Estimation) was not harvested; the 23 samples below come from 4 community repositories.

Syntology 23 code samples harvested from 4 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 23 samples from 4 repositories, 18 ran (16 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

61 repositories listed; official and paper-mentioned ones first.

ZheC/Realtime_Multi-Person_Pose_Estimation officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
AkashGanesan/PedestrianAttention mentioned on GitHubSyntology: not harvested report
CMU-Perceptual-Computing-Lab/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
CMU-Perceptual-Computing-Lab/openpose_unity_plugin mentioned on GitHubNOASSERTIONSyntology: not harvested report
ChetanTayal138/HAR-Web mentioned on GitHubtfSyntology: not harvested report
D1vyansh/BodyJointDetection mentioned on GitHubpytorchSyntology: not harvested report
DavHoffmann/LearningToTrainWithSyntheticHumans mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
Joyce511/OpenVino_Realtime_Multi-Person_Pose_Estimation mentioned on GitHubSyntology: not harvested report
Kaif10/Pose-Detection mentioned on GitHubSyntology: not harvested report
KarinaKorsgaard/Bartender-AI-OpenPose-Osc-Sender mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
MSeeker1340/Vision2018-Pose mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MayankGupta73/Workout-Evaluation-tf-openpose mentioned on GitHubtfSyntology: not harvested report
Nikhil619/Motion-direction-control-of-a-pi-robot-using-hand-movementss mentioned on GitHubApache-2.0Syntology: not harvested report
Sobeit-Tim/NuguEyeTest mentioned on GitHubSyntology: not harvested report
anatolix/keras_Realtime_Multi-Person_Pose_Estimation mentioned on GitHubNOASSERTIONSyntology: not harvested report
baodi23/hourglass-facekeypoints-detection mentioned on GitHubpytorchSyntology: not harvested report
blake58/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
chengguixiong1010/rnn_STAF_2dpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
fcr3/OpenVINO_Tutorials mentioned on GitHubtfSyntology: not harvested report
fcr3/wine_detector mentioned on GitHubtfSyntology: not harvested report
fengyidong123/openpose-master mentioned on GitHubpytorchSyntology: not harvested report
goutern/PoseEstimation mentioned on GitHubpytorchSyntology: not harvested report
harshalsonioo1/hpe mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ibm/max-human-pose-estimator mentioned on GitHubtfApache-2.0Syntology: 18 samples, 13 ran (0 instrument-failed) · 5 unverified report
jarrodanderson/openpose-demo mentioned on GitHubpytorchSyntology: not harvested report
jreisam/Unity-OpenPose-Edutable mentioned on GitHubNOASSERTIONSyntology: not harvested report
ken724049/action-recognition mentioned on GitHubSyntology: not harvested report
krishnac7/OpenPose mentioned on GitHubSyntology: not harvested report
krutikabapat/Deep-Learning-based-OpenPose-Estimation mentioned on GitHubSyntology: not harvested report
laobaiswag/openpose1 mentioned on GitHubpytorchSyntology: not harvested report
liang-faan/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
lncarter/Openpose mentioned on GitHubpytorchSyntology: not harvested report
lwxGitHub123/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
lwxGitHub123/openpose20200610 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
mgolnezhad/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
mohammadreyaz/openposered mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
mohammadreyaz/pose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
oublalkhalid/AI-OpenPose mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
qdhill/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
quic/aimet-model-zoo mentioned on GitHubpytorchSyntology: not harvested report
radioactiverockets/OpenPoseBreackoutGame mentioned on GitHubNOASSERTIONSyntology: not harvested report
raymon-tian/hourglass-facekeypoints-detection mentioned on GitHubpytorchSyntology: not harvested report
saadbutt32/Pakistan-Sign-Language-Interpreter mentioned on GitHubGPL-3.0Syntology: not harvested report
sananand007/Xrelab mentioned on GitHubtfSyntology: not harvested report
shihenw/convolutional-pose-machines-release mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
soulslicer/staf mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
starman360/openpose_xavier mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
techforgood-kiran/ai mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
theyellowdiary/openpose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
xaoch/rapJetson2 mentioned on GitHubpytorchSyntology: not harvested report
xar47x/pose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
xiaozeguo123/-Quick-Capture-system-HSR mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yikegami/openpose mentioned on GitHubpytorchSyntology: not harvested report
yinzhiyan43/openpose-dev mentioned on GitHubpytorchSyntology: not harvested report
yongsheng268/OpenPose mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhaoqyu/openpose-mge-pt mentioned on GitHubpytorchSyntology: not harvested report
zyxcambridge/openpose_all mentioned on GitHubpytorchSyntology: not harvested report
Xingyu-Romantic/RMPose_PAF paddleSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

23 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran; the contract check could not run
14ran
5unverified

Licence: 4 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

DavHoffmann/LearningToTrainWithSyntheticHumans community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
compute_gt_teacher tf_pose/train_with_adversarial_teacher.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · f4d54c84f9d6d11f · report fixture: signature probabilities:ndarray/1/float, picked:ndarray/1/bool, alpha:float/0/float, beta:float/0/float, teacher_loss_type:str/0/str, loss_last:float/0/float, loss_current:float/0/float, nbins_nrs:ndarray/1/int, nbins:list/1/int · returned ndarray · level recorded 2026-09-22
round_int tf_pose/eval_MPI.py ran · honoured contract fingerprinted licence not identified · pointer only · 244255938544c7a6 · report fixture: signature val:float/0/float · returned int · level recorded 2026-09-22
MSeeker1340/Vision2018-Pose community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
plot_result src/plot.py ran fingerprinted MIT (permissive) · 822b0c684ba9eba6 · report fixture: signature y:ndarray/3/float, f:int/0/int · returned ndarray · level recorded 2026-09-26
ibm/max-human-pose-estimator community (archive-listed) 18 samples, 13 ran (0 instrument-failed) · 5 unverified
arrayCast core/tf_pose/slidingwindow/ArrayUtils.py ran Apache-2.0 (permissive) · 20375b6e697cb883 · report fixture: returned ndarray · level recorded 2026-09-26
arrayFactory core/tf_pose/slidingwindow/ArrayUtils.py ran Apache-2.0 (permissive) · 967290f028bec7f8 · report fixture: returned ndarray · level recorded 2026-09-26
batchWindows core/tf_pose/slidingwindow/Batching.py ran fingerprinted Apache-2.0 (permissive) · 92fd1e2b70b24c05 · report fixture: signature windows:list/1/ndarray, batchSize:int/0/int · returned list · level recorded 2026-09-26
cropRect core/tf_pose/slidingwindow/RectangleUtils.py ran Apache-2.0 (permissive) · eb150ddc7184f446 · report fixture: signature rect:tuple/1/int, cropTop:int/0/int, cropBottom:int/0/int, cropLeft:int/0/int, cropRight:int/0/int · returned tuple · level recorded 2026-09-26
cropRectEqually core/tf_pose/slidingwindow/RectangleUtils.py ran fingerprinted Apache-2.0 (permissive) · 630ac0a9f50488c4 · report fixture: signature rect:tuple/1/int, cropping:int/0/int · returned tuple · level recorded 2026-09-26
generate in 143 papers
census: 5 implementations from 6 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
core/tf_pose/slidingwindow/SlidingWindow.py ran Apache-2.0 (permissive) · cdb1c9715688f9a1 · report fixture: signature data:Tensor/3/float, dimOrder:list/1/str, maxWindowSizeW:int/0/int, maxWindowSizeH:int/0/int, overlapPercent:float/0/float, transforms:list/1/callable · returned list · level recorded 2026-09-26
generateForSize core/tf_pose/slidingwindow/SlidingWindow.py ran Apache-2.0 (permissive) · 93c5229a4050e760 · report fixture: signature width:int/0/int, height:int/0/int, dimOrder:list/1/str, maxWindowSizeW:int/0/int, maxWindowSizeH:int/0/int, overlapPercent:float/0/float, transforms:list/1/callable · returned list · level recorded 2026-09-26
get_sample_images core/tf_pose/common.py ran Apache-2.0 (permissive) · 1cb22812d63a8d83 · report fixture: signature w:int/0/int, h:int/0/int · returned list · level recorded 2026-09-26
layer in 12 papers core/tf_pose/tensblur/smoother.py ran Apache-2.0 (permissive) · 1fb38eb9d6522fb0 · report fixture: signature op:callable/0/? · returned function · level recorded 2026-09-26
model_wh core/tf_pose/networks.py ran Apache-2.0 (permissive) · f8b79dbb86b46205 · report fixture: signature resolution_str:str/0/str · returned tuple · level recorded 2026-09-26
padRect core/tf_pose/slidingwindow/RectangleUtils.py ran Apache-2.0 (permissive) · d8dbe9ff57d30fbc · report fixture: signature rect:tuple/1/int, padTop:int/0/int, padBottom:int/0/int, padLeft:int/0/int, padRight:int/0/int, bounds:tuple/1/int, clipExcess:bool/0/bool · returned tuple · level recorded 2026-09-26
read_imgfile core/tf_pose/common.py ran Apache-2.0 (permissive) · 1440a7103327c0de · report fixture: signature path:str/0/str, width:int/0/int, height:int/0/int · returned ndarray · level recorded 2026-09-26
zerosFactory core/tf_pose/slidingwindow/ArrayUtils.py ran Apache-2.0 (permissive) · e25580edeb9875ea · report fixture: returned ndarray · level recorded 2026-09-26
generateDistanceMatrix core/tf_pose/slidingwindow/WindowDistance.py unverified Apache-2.0 (permissive) · 1fc7d25ab7ceeb40 · report
get_part_cid core/tf_pose/pafprocess/pafprocess.py unverified Apache-2.0 (permissive) · 0ad190b8ea7cf881 · report
get_score in 56 papers core/tf_pose/pafprocess/pafprocess.py unverified Apache-2.0 (permissive) · 418d24f644276625 · report
mergeWindows core/tf_pose/slidingwindow/Merging.py unverified Apache-2.0 (permissive) · 33f87ef10f320887 · report
process_paf core/tf_pose/pafprocess/pafprocess.py unverified Apache-2.0 (permissive) · dd2c2980939419d2 · report
Xingyu-Romantic/RMPose_PAF community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 11 of 11, arg 1: rank 3, kind int, dtype uint8
testing/test_pose.py ran · violated contract fingerprinted no licence file found · pointer only · 9d8d1b763badb5e7 · report fixture: signature origin_img:ndarray/3/int · returned ndarray · level recorded 2026-09-22
padRightDownCorner testing/test_pose.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 1273c2cd8619f6cb · report fixture: signature img:ndarray/3/int, stride:int/0/int, padValue:int/0/int · returned tuple · level recorded 2026-09-22

Tasks

2D Human Pose Estimation2D Pose EstimationKeypoint DetectionMulti-Person Pose EstimationObject DetectionPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation COCO-WholeBody OpenPose WB 33.8 #14 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody OpenPose body 56.3 #14 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody OpenPose face 48.2 #14 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody OpenPose foot 53.2 #14 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody OpenPose hand 19.8 #14 of 15 Archive leaderboard report
Keypoint Detection COCO Part Affinity Fields Validation AP 60.5 #2 of 2 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose AP50 84.9 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose AP75 67.5 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose APL 68.2 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose APM 57.1 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose AR 66.5 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose AR50 87.2 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose ARL 74.6 #15 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev CMU Pose ARM 60.6 #15 of 16 Archive leaderboard report
Keypoint Detection MPII Multi-Person Part Affinity Fields mAP@0.5 75.6% #6 of 9 Archive leaderboard report
Multi-Person Pose Estimation COCO CMU-Pose AP 0.618 #1 of 1 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev CMU-Pose AP 61.8 #14 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev CMU-Pose AP50 84.9 #14 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev CMU-Pose AP75 67.5 #14 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev CMU-Pose APL 68.2 #14 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev CMU-Pose APM 57.1 #14 of 15 Archive leaderboard report
Multi-Person Pose Estimation MPII Multi-Person Part Affinity Fields AP 75.6% #6 of 9 Archive leaderboard report
Pose Estimation COCO test-dev CMU-Pose AP 61.8 #44 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CMU-Pose AP50 84.9 #44 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CMU-Pose AP75 67.5 #44 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CMU-Pose APL 68.2 #44 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CMU-Pose APM 57.1 #44 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CMU-Pose AR 66.5 #44 of 47 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: PAFs

PAFs

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections