OpenCodePapers

3d-human-pose-estimation-on-emdb

Pose Estimation3D Human Pose Estimation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAverage MPJPE-PA (mm)Average MPJPE (mm)Average MVE (mm)Average MVE-PA (mm)Average MPJAE (deg)Average MPJAE-PA (deg)Jitter (10m/s^3)ModelNameReleaseDate
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos✓ Link45.774.486.6TRAM2024-03-26
WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion✓ Link50.479.794.4WHAM (ViT)2023-12-12
GenHMR: Generative Human Mesh Recovery51.788.299.5GenHMR2024-12-19
BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos52.192.598.9BioPose2025-01-14
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation✓ Link65.5935103.037122.19380.367824.517423.070449.2068HybrIK2020-11-30
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers✓ Link66.794108.107119.2381.1847185.933FastMETRO-L no SMPL Head2022-07-27
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation✓ Link68.7969103.134122.88481.327523.093321.626555.4525CLIFF2022-08-01
GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras✓ Link71.0091107.797128.23785.458625.505823.548467.3522GLAMR2021-12-02
PARE: Part Attention Regressor for 3D Human Body Estimation✓ Link72.203113.887133.24785.378824.67322.384275.1137PARE2021-04-17
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers✓ Link72.6765115.036133.56686.004325.0722.948281.2959FastMETRO-L2022-07-27
Monocular, One-stage, Regression of Multiple 3D People✓ Link75.1869112.652134.86390.64826.597523.990171.2556ROMP2020-08-27
Human Body Model Fitting by Learned Gradient Descent81.1389115.82140.6395.725525.157225.642572.9695LGD2020-08-19
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop✓ Link82.8502131.065159.95698.130528.455525.703381.8447PyMAF2021-03-30
Check out how to contribute new results.