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 351375 of 665 papers

TitleStatusHype
Sequential 3D Human Pose Estimation Using Adaptive Point Cloud Sampling StrategyCode1
DECA: Deep viewpoint-Equivariant human pose estimation using Capsule AutoencodersCode1
Self-Supervised 3D Human Pose Estimation with Multiple-View GeometryCode0
Learning Skeletal Graph Neural Networks for Hard 3D Pose EstimationCode0
FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and IntegrationCode2
MetaPose: Fast 3D Pose from Multiple Views without 3D SupervisionCode0
VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild0
LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh RenderingCode1
Probabilistic Monocular 3D Human Pose Estimation with Normalizing FlowsCode1
Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose EstimationCode1
Learning Local Recurrent Models for Human Mesh Recovery0
Human Pose Regression with Residual Log-likelihood EstimationCode1
Conditional Directed Graph Convolution for 3D Human Pose EstimationCode1
Everybody Is Unique: Towards Unbiased Human Mesh Recovery0
PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation0
Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge SensorsCode1
Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos0
Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and TrackingCode1
Intelligent Carpet: Inferring 3D Human Pose From Tactile Signals0
THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers0
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking0
SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency0
3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training0
Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose DataCode0
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network0
Show:102550
← PrevPage 15 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Simple-baselinePA-MPJPE157Unverified
2HMRMPJPE130Unverified
3BMPMPVPE119.3Unverified
4SPINMPVPE116.4Unverified
5Wenshuo et a;.MPVPE112.6Unverified
6TCMR (T=16 w/o 3DPW)MPVPE111.5Unverified
7CHOMPMPVPE110.1Unverified
8PC-HMRMPVPE108.6Unverified
93DCrowdNetMPVPE108.5Unverified
10SMPLifyPA-MPJPE106.8Unverified
#ModelMetricClaimedVerifiedStatus
1VNect (Augm.)MPJPE124.7Unverified
2HMRMPJPE124.2Unverified
3Single-Shot Multi-PersonMPJPE122.2Unverified
4MehtaMPJPE117.6Unverified
5PONetMPJPE115Unverified
6Pose Consensus (monocular)MPJPE112.1Unverified
7GeoRep (fully-supervised)MPJPE110.8Unverified
8XFormer (HRNet)MPJPE109.8Unverified
9EpipolarPose (fully-supervised)MPJPE108.99Unverified
10SPINMPJPE105.2Unverified