Papers › Stacked Hourglass Networks for Human Pose Estimation

Stacked Hourglass Networks for Human Pose Estimation

22 Mar 2016arXiv:1603.06937archive 2025-07-28

Alejandro Newell, Kaiyu Yang, Jia Deng

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

PaperPDFCodeCode 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

Syntology 25 code samples harvested from 5 repositories linked to this paper: 24 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 25 samples from 5 repositories, 24 ran (22 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 5 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. 1 of the 24 samples that ran has no recorded date.

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

BB-Repos/BBpose mentioned on GitHubtfMITSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
Barak123748596/CVDL_course_project mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
Epsilon456/Face_LandMark_Recognition mentioned on GitHubtfSyntology: not harvested report
MandyMo/pytorch_HMR mentioned on GitHubpytorchSyntology: not harvested report
SimonWT/cv-project-2020 mentioned on GitHubpytorchSyntology: not harvested report
TariqBerrada/Pose-Estimation-with-Stacked-Hourglass mentioned on GitHubtfSyntology: not harvested report
adipandas/torch_shnet mentioned on GitHubpytorchSyntology: not harvested report
anibali/dsnt-pose2d mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
baodi23/hourglass-facekeypoints-detection mentioned on GitHubpytorchSyntology: not harvested report
bearpaw/pytorch-pose mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
benjs/hourglass_networks mentioned on GitHubtfApache-2.0Syntology: not harvested report
bordac6/PNNPPV_project mentioned on GitHubpytorchSyntology: not harvested report
chanyn/3Dpose_ssl mentioned on GitHubtfSyntology: not harvested report
chenyouxin113/sota-status-investigation mentioned on GitHubtfSyntology: not harvested report
danny1984/hourglass_keras mentioned on GitHubpytorchSyntology: not harvested report
efeatikkan/Human_Pose_Estimation mentioned on GitHubtfSyntology: not harvested report
geopavlakos/c2f-vol-demo mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
geopavlakos/c2f-vol-train mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
geopavlakos/object3d mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
geopavlakos/ordinal-pose3d mentioned on GitHubpytorchSyntology: not harvested report
karlgodin/DP10-hockey-pose-estimation mentioned on GitHubpytorchSyntology: not harvested report
motlabs/dont-be-turtle mentioned on GitHubtfSyntology: not harvested report
neherh/HyperStackNet mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
paulmthompson/StackedHourglass.jl mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
princeton-vl/pose-hg-demo mentioned on GitHubtorchBSD-3-ClauseSyntology: not harvested report
raymon-tian/hourglass-facekeypoints-detection mentioned on GitHubpytorchSyntology: not harvested report
salinasJJ/BBpose mentioned on GitHubtfMITSyntology: not harvested report
samson6460/tf2_pose_estimation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified) and Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method. report
siyliepfl/deformation-aware-unpaired-image-translation mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
tanreinama/XceptionHourgrass---PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
umich-vl/pose-hg-demo mentioned on GitHubtorchBSD-3-ClauseSyntology: not harvested report
umich-vl/pose-hg-train mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
varunvprabhu/simple_pose_hourglass mentioned on GitHubtfSyntology: not harvested report
wbenbihi/hourglasstensorflow mentioned on GitHubtfMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
wbenbihi/hourglasstensorlfow mentioned on GitHubtfMITSyntology: not harvested report
yuanyuanli85/Stacked_Hourglass_Network_Keras mentioned on GitHubpytorchSyntology: not harvested report
zhiqic/chartreader mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ChartReader: A Unified Framework for Chart Derendering and Comprehension without... (arXiv:2304.02173; that paper's own run record: 16 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 10 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-217 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code7 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code3 mindsporeSyntology: not harvested report
jgraving/DeepPoseKit tfApache-2.0Syntology: not harvested 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
open-mmlab/mmpose pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
txyugood/PaddlePose paddleSyntology: not harvested report
yangyucheng000/StackedHourglass mindsporeApache-2.0Syntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified 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

25 samples harvested: 24 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 2 where Syntology's instrument failed) · 1 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 · our draft was wrong
1ran; the contract check could not run
22ran
1unverified

Licence: 1 of the 25 samples is 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 5 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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 1 sample 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.

BB-Repos/BBpose community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
coord_transform bbpose/preprocess/utils.py ran MIT (permissive) · ede58fc3ba58ed25 · report fixture: signature coords:EagerTensor/1/float, center:list/1/float, scale:float/0/float, rotation:float/0/float, invert:int/0/int, size:int/0/int · returned EagerTensor · level recorded 2026-09-26
filter_params bbpose/utils.py ran MIT (permissive) · 6dbfb45b1ac19409 · report fixture: signature param_dict:dict/0/? · returned dict · level recorded 2026-09-26
get_max_indices bbpose/train/utils.py ran MIT (permissive) · eec92c49784b6838 · report fixture: signature heatmaps:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-26
get_transformation_matrix bbpose/preprocess/utils.py ran MIT (permissive) · 2092249af2b2fe48 · report fixture: signature center:EagerTensor/1/float, scale:float/0/float, rotation:float/0/float, invert:int/0/int, size:int/0/int · returned EagerTensor · level recorded 2026-09-26
get_type in 7 papers bbpose/utils.py ran fingerprinted MIT (permissive) · ccea79b6b915e1b5 · report fixture: signature param:str/0/str · returned str · level recorded 2026-09-26
rotate_transformation_matrix bbpose/preprocess/utils.py ran MIT (permissive) · 4dbdf834bb0a03f6 · report fixture: signature transfromation_matrix:EagerTensor/2/float, rotation:EagerTensor/0/float, size:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-26
type_check bbpose/utils.py ran fingerprinted MIT (permissive) · cf51336d7aeaf3d7 · report fixture: signature param:str/0/str, value:str/0/str · returned bool · level recorded 2026-09-26
siyliepfl/deformation-aware-unpaired-image-translation community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
genertate_heatmap util/util.py ran MIT (permissive) · 6b3e458447bde8c3 · report fixture: signature imSize:tuple/1/int, keypoints:ndarray/2/float, sigma:float/0/float · returned ndarray · level recorded 2026-09-26
getBaseGrid models/deform_transfer_model.py ran MIT (permissive) · dd1c3c1cc330faf5 · report fixture: signature N:int/0/int, normalize:bool/0/bool, getbatch:bool/0/bool, batchSize:int/0/int · returned Tensor · level recorded 2026-09-26
get_norm_layer in 111 papers models/networks.py ran MIT (permissive) · 30190c576dd53b28 · report fixture: signature norm_type:str/0/str · returned partial · level recorded 2026-09-24
get_scheduler in 122 papers models/networks.py ran MIT (permissive) · 0dacd083f5b40969 · report fixture: signature optimizer:Adam/0/?, opt:OptConfig/0/?, Isdeform:bool/0/bool · returned LambdaLR · level recorded 2026-09-26
putGaussianMaps util/util.py ran MIT (permissive) · 7dc7eef5b6e0e070 · report fixture: signature center:tuple/1/float, accumulate_confid_map:ndarray/2/float, sigma:float/0/float, im_size:tuple/1/int · returned ndarray · level recorded 2026-09-26
tensor2im in 30 papers util/util.py ran MIT (permissive) · 72de6d76704ce9f0 · report fixture: returned ndarray · level recorded 2026-09-26
visualize_patchGAN util/visualizer.py ran MIT (permissive) · 1ae175fe4202fb3f · report fixture: signature source_img:Image/0/?, feature_map:ndarray/3/int, color:str/0/str, alpha:float/0/float · returned Image · level recorded 2026-09-26
draw_deformation util/visualizer.py unverified MIT (permissive) · 1ff0d56adf6352ad · report
tanreinama/XceptionHourgrass---PyTorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
xceptionhourgrass.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 6a59ba4afdd39102 · report fixture: returned Tensor · level recorded, date not recorded
wbenbihi/hourglasstensorflow community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
build_release_tag ci/readme.py ran fingerprinted MIT (permissive) · 10b27358398f2cb0 · report fixture: signature version:str/0/str · returned str · level recorded 2026-09-26
get_groups in 12 papers ci/changelog.py ran MIT (permissive) · 8da26b7cda8f4004 · report fixture: signature m:Match/0/? · returned dict · level recorded 2026-09-26
get_tags_position ci/readme.py ran MIT (permissive) · ae6a5d4d6122a4d0 · report fixture: signature lines:list/1/str · returned tuple · level recorded 2026-09-26
group_commits_strings ci/changelog.py ran MIT (permissive) · dfe90fd4f8760f6c · report fixture: signature lines:list/1/str · returned list · level recorded 2026-09-26
parse_readme ci/readme.py ran fingerprinted MIT (permissive) · b8877366aa9f23ef · report fixture: signature readme:str/0/str · returned list · level recorded 2026-09-26
yangyucheng000/StackedHourglass community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
match_format postprocess.py ran Apache-2.0 (permissive) · 7fc99ca12fb3528d · report fixture: signature dic:dict/0/? · returned list · level recorded 2026-09-26
merge in 85 papers model_utils/config.py ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report fixture: signature args:Namespace/0/?, cfg:dict/0/? · returned dict · level recorded 2026-09-22
parse_cli_to_yaml in 29 papers model_utils/config.py ran Apache-2.0 (permissive) · 738456e1b7388e7e · report fixture: signature parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str · returned Namespace · level recorded 2026-09-24
parse_yaml in 32 papers model_utils/config.py ran Apache-2.0 (permissive) · 96a9939953d5992d · report fixture: signature yaml_path:str/0/str · returned tuple · level recorded 2026-09-25

Tasks

Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation FLIC Elbows Stacked Hourglass Networks PCK@0.2 99.0% #1 of 2 Archive leaderboard report
Pose Estimation FLIC Wrists Stacked Hourglass Networks PCK@0.2 97.0% #1 of 2 Archive leaderboard report
Pose Estimation MPII Human Pose Stacked Hourglass Networks PCKh-0.5 90.9 #24 of 46 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: Stacked Hourglass Network

1x1 ConvolutionBatch NormalizationConvolutionHourglass ModuleMax PoolingRMSPropReLUResidual ConnectionStacked Hourglass NetworkStep Decay

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