Browse State-of-the-Art › 3D Human Pose Estimation

3D Human Pose Estimation

353 papers with code · 26 benchmarks · 50 datasets archive 2025-07-28

Computer Vision

3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

26 leaderboard tables shown for this task, 26 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 26 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Panoptic (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
3DPW (119 rows) ExtPose (-a, T=16) ExtPose: Robust and Coherent Pose Estimation by Extending ViTs — — Compare
MPI-INF-3DHP (108 rows) TCPFormer (T=81) TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy... code — Compare
Human3.6M (88 rows) LMT R152 384x384 Learnable human mesh triangulation for 3D human pose and shape estimation — — Compare
HumanEva-I (31 rows) GLA-GCN (T=27, GT) GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D... code — Compare
H3WB (17 rows) SemGAN 3D WholeBody Pose Estimation based on Semantic Graph Attention... — — Compare
Total Capture (14 rows) AdaFuse AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose... code Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
EMDB (13 rows) TRAM TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
AGORA (11 rows) NIKI (Twist-and-Swing) NIKI: Neural Inverse Kinematics with Invertible Neural Networks... code Syntology official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 1 unverified Compare
Panoptic (9 rows) TesseTrack Multi-View (5 views) TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking — — Compare
Surreal (6 rows) VirtualMarker 3D Human Mesh Estimation from Virtual Markers code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified Compare
3D Poses in the Wild Challenge (5 rows) BeyondWeak Beyond Weak Perspective for Monocular 3D Human Pose Estimation — — Compare
AIST++ (5 rows) RobustCap Fusing Monocular Images and Sparse IMU Signals for Real-time Human... code — Compare
RICH (4 rows) UPose3D (eval only) UPose3D: Uncertainty-Aware 3D Human Pose Estimation with... — — Compare
SLOPER4D (4 rows) LiDAR-HMR LiDAR-HMR: 3D Human Mesh Recovery from LiDAR code — Compare
UBody (4 rows) Multi-HMR Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
SkiPose (3 rows) MetaPose (S1+S2) MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision code — Compare
DHP19 (2 rows) Point Transformer Efficient Human Pose Estimation via 3D Event Point Cloud code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified Compare
Geometric Pose Affordance (2 rows) ResNet-F Geometric Pose Affordance: 3D Human Pose with Scene Constraints — — Compare
SPEC-MTP (2 rows) W-HMR W-HMR: Monocular Human Mesh Recovery in World Space with... code — Compare
3DOH50K (1 row) OOH Object-Occluded Human Shape and Pose Estimation From a Single Color Image — — Compare
CHALL H80K (1 row) ResNet An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge code — Compare
Geometric Pose Affordance (1 row) Baseline model Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach code — Compare
HSPACE (1 row) T-THUNDR (HITI + HSPACE) HSPACE: Synthetic Parametric Humans Animated in Complex Environments — — Compare
ITOP front-view (1 row) SPiKE SPiKE: 3D Human Pose from Point Cloud Sequences code — Compare
JTA (1 row) Dual network Dual networks based 3D Multi-Person Pose Estimation from Monocular Video code — Compare
Waymo Open Dataset (1 row) VoxelKP VoxelKP: A Voxel-based Network Architecture for Human Keypoint... 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

50 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 50 until expanded.

Subtasks archive 2025-07-28

9 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 665 · with a code link: 353 · where Syntology ran a sample: 94 (79 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (94 of 665 tagged: 79 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument)

Page 1 of 7: papers 1 to 100 of 665, 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 34 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