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 5175 of 665 papers

TitleStatusHype
Double-chain Constraints for 3D Human Pose Estimation in Images and VideosCode1
DiffPose: Toward More Reliable 3D Pose EstimationCode1
3D Human Mesh Regression with Dense CorrespondenceCode1
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis AggregationCode1
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the WildCode1
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion PredictionCode1
Efficient Domain Adaptation via Generative Prior for 3D Infant Pose EstimationCode1
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion GenerationCode1
A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose EstimationCode1
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose EstimationCode1
ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D PosesCode1
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
Deformable Mesh Transformer for 3D Human Mesh RecoveryCode1
3D human pose estimation in video with temporal convolutions and semi-supervised trainingCode1
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose EstimationCode1
Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a VideoCode1
DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose EstimationCode1
Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View CamerasCode1
End-to-End Human Pose and Mesh Reconstruction with TransformersCode1
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationCode1
3D-LFM: Lifting Foundation ModelCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose EstimationCode1
Show:102550
← PrevPage 3 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