SOTAVerified

3D Human Pose Estimation

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.

Papers

Showing 110 of 665 papers

TitleStatusHype
Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images0
ExtPose: Robust and Coherent Pose Estimation by Extending ViTs0
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose EstimationCode0
Learning Pyramid-structured Long-range Dependencies for 3D Human Pose EstimationCode0
UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction0
PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose EstimationCode1
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose EstimationCode0
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation0
3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware TransformerCode0
Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms0
Show:102550
← PrevPage 1 of 67Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CanonPoseAverage MPJPE (mm)74.3Unverified
2VIBEAverage MPJPE (mm)65.6Unverified
3VoxelKeypointFusion (transfer)Average MPJPE (mm)64.3Unverified
4SIM (SH detections FT) (MA)Average MPJPE (mm)62.9Unverified
52D-3D Lifting self-supervisedAverage MPJPE (mm)62Unverified
6Probabilistic Monocular (T=1)Average MPJPE (mm)61.8Unverified
7TAPE (T=16)Average MPJPE (mm)60Unverified
8Sequence-to-sequence networkAverage MPJPE (mm)58.5Unverified
9Stereoscopic View Synthesis SubnetworkAverage MPJPE (mm)58Unverified
10SemGCNAverage MPJPE (mm)57.6Unverified