Browse State-of-the-Art › Pose Estimation

Pose Estimation

1,679 papers with code · 31 benchmarks · 124 datasets archive 2025-07-28

Computer Vision

Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.

A common benchmark for this task is MPII Human Pose

( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

31 leaderboard tables shown for this task, 31 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 31 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
COCO test-dev (47 rows) ViTPose (ViTAE-G, ensemble) ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation code Syntology community repositories only · 18 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified Compare
MPII Human Pose (46 rows) PCT (swin-l, test set) Human Pose as Compositional Tokens code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
OCHuman (19 rows) ViTPose (ViTAE-G, GT bounding boxes) ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation code Syntology community repositories only · 18 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified Compare
Leeds Sports Poses (18 rows) OmniPose OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation code — Compare
CrowdPose (12 rows) BUCTD-W48 (w/cond. input from PETR, and generative sampling) Rethinking pose estimation in crowds: overcoming the detection... code Syntology official (archive's flag): 4 ran · 4 ran (of which 3 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) · 2 unverified Compare
COCO val2017 (11 rows) CCNet (ViTPose-B_GT-bbox_256x192) On the Calibration of Human Pose Estimation — — Compare
AIC (10 rows) Hulk(Finetune, ViT-L) Hulk: A Universal Knowledge Translator for Human-Centric Tasks code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 11 unverified Compare
COCO (Common Objects in Context) (10 rows) OmniPose (WASPv2) OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation code — Compare
ITOP front-view (7 rows) AdaPose Sequential 3D Human Pose Estimation Using Adaptive Point Cloud... code — Compare
InLoc (6 rows) GIM-DKM GIM: Learning Generalizable Image Matcher From Internet Videos code Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified Compare
ITOP top-view (5 rows) DECA-D3 DECA: Deep viewpoint-Equivariant human pose estimation using... code — Compare
J-HMDB (5 rows) SimpleBaseline + HANet Kinematic-aware Hierarchical Attention Network for Human Pose... code — Compare
MPII Single Person (5 rows) 4xRSN-50 Learning Delicate Local Representations for Multi-Person Pose Estimation code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
UPenn Action (5 rows) OmniPose OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation code — Compare
DensePose-COCO (4 rows) DP-RCNN-DeepLab (ResNet-101) Continuous Surface Embeddings code Syntology community repositories only · 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
SALSA (4 rows) SubdivNet Subdivision-Based Mesh Convolution Networks code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
300W (Full) (3 rows) SPIGA Shape Preserving Facial Landmarks with Graph Attention Networks code — Compare
BRACE (2 rows) HRNet fine-tuned on BRACE Deep High-Resolution Representation Learning for Human Pose Estimation code Syntology official (archive's flag): 8 ran · 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified Compare
COCO 2017 val (2 rows) LOGO-CAP (Ours) HRNet-W48 — — — Compare
FLIC Elbows (2 rows) Stacked Hourglass Networks Stacked Hourglass Networks for Human Pose Estimation code Syntology 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 Compare
FLIC Wrists (2 rows) Stacked Hourglass Networks Stacked Hourglass Networks for Human Pose Estimation code Syntology 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 Compare
UAV-Human (2 rows) AlphaPose RMPE: Regional Multi-person Pose Estimation code — Compare
!(()&&!|*|*| (1 row) Nate Neural Ordinary Differential Equations code Syntology community repositories only · 98 ran (of which 44 constructed an object rather than computing a result; 64 with no instrument failure: 2 honoured, 5 violated, 57 with no contract checked; 34 where Syntology's instrument failed) · 26 unverified Compare
3DPW (1 row) HybridCap HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions — — Compare
ApolloCar3D (1 row) GSNet GSNet: Joint Vehicle Pose and Shape Reconstruction with... code — Compare
COCO minival (1 row) MSPN Rethinking on Multi-Stage Networks for Human Pose Estimation code — Compare
KITTI 2015 (1 row) GeoNet GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose code Syntology official (archive's flag): 4 ran · 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) · 4 unverified Compare
MERL-RAV (1 row) SPIGA Shape Preserving Facial Landmarks with Graph Attention Networks code — Compare
MPII (1 row) OmniPose (WASPv2) OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation code — Compare
MS-COCO (1 row) UniHCP (finetune) UniHCP: A Unified Model for Human-Centric Perceptions code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified Compare
Pix3D (1 row) Mid-Level based Object Pose Estimation using Mid-level Visual Representations code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

124 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 124 until expanded.

COCO (Common Objects in Context)KITTIMPII3DPWAMASS10,000 People - Human Pose Recognition DataDensePoseJHMDBPASCAL3D+300WLSPYCB-VideoMPII Human PosePix3DLFPWSUN3DNCLTPenn ActionCrowdPoseAachen Day-NightInLocOCHumanTotalCaptureInterHand2.6MUAV-HumanFLICGazeFollowJTAMuCo-3DHPCOCO-WholeBodyMannequinChallengeAnimal KingdomIKEA ASMINRIA PersonKeypointNetITOPAnimal-Pose DatasetModaNetSALSAApolloCar3D3D Hand PoseFirst-Person Hand Action BenchmarkMSRA HandSVIROAICMVOREgoDexterMoViSLOPER4DUnrealEgoUnite the PeoplexR-EgoPoseCarFusionEgoCapHUMAN4DATRWGPAH3WBIMUPoserBiwi Kinect Head PoseHandNetKITTI Odometry BenchmarkMonoPerfCap DatasetSynthHandsFATYCBInEOAT DatasetYoga-82BRACEDREAM-datasetPedXFewSOLFraunhofer IPA Bin-PickingHuPRMERL-RAVSportsPoseAmateur DrawingsCHAIRS datasetComposable activities datasetCORSMALFitness-AQAHOPE-ImageHOPE-VideoICVL Hand PosturePoPArtVBRBASEPRODDrunkard's DatasetMBW - Zoo DatasetMOTFrontMPHOI-72Parkinson's Pose Estimation DatasetPoserRendered Handpose DatasetRetinal MicrosurgerySLAM2REFUBC3V DatasetVRMocap: VR Mocap Dataset for Pose ReconstructionBigHand2.2M BenchmarkCIPConSLAMCOPE-119Data for "Image-based Backbone Reconstruction for Non-Slender Soft Robots"DensePose-TrackDesert LocustFine-grained 3D PoseHalpe-FullBodyHumanoidRobotPoseImmediacy DatasetiMoCapMacaquePoseNToPOmniLabRealArt-6SIDODSMOTStore datasetStreet View Image, Pose, and 3D Cities DatasetSymmetric SolidsVinegar FlyVR Mocap Dataset for Pose/Orientation PredictionGrévy’s ZebraICT-3DHPInfiniteRepPose Estimation Lunar Robot

Subtasks archive 2025-07-28

17 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 4,228 · with a code link: 1,679 · where Syntology ran a sample: 376 (325 with a run with no instrument failure, 51 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (376 of 4,228 tagged: 325 with a run with no instrument failure, 51 where every run was a failure of Syntology's instrument)

Page 1 of 43: papers 1 to 100 of 4,228, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 52 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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