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 1–10 of 665 papers

TitleStatusHype
Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images—0
ExtPose: Robust and Coherent Pose Estimation by Extending ViTs—0
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 Interaction—0
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 Estimation—0
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 Transforms—0
Show:102550
← PrevPage 1 of 67Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CanonPoseMPJPE264.4—Unverified
2SimpleBaselineMPJPE252—Unverified
3CanonPoseMPJPE193.7—Unverified
4SHN + SimpleBaselineMPJPE189.6—Unverified
5CanonPose + 3D supervisionMPJPE155.9—Unverified
6Resnet50MPJPE151.6—Unverified
7CPN + JointformerMPJPE142.8—Unverified
8Large SimpleBaselineMPJPE131.6—Unverified
9SimpleBaselineMPJPE125.7—Unverified
10CanonPose + 3D supervisionMPJPE117.5—Unverified