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 101125 of 665 papers

TitleStatusHype
Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic DataCode1
Body Meshes as PointsCode1
GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D PoseCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with TransformersCode1
HDFormer: High-order Directed Transformer for 3D Human Pose EstimationCode1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
EM-POSE: 3D Human Pose Estimation From Sparse Electromagnetic TrackersCode1
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-LearningCode1
Deep Learning-Based Human Pose Estimation: A SurveyCode1
3D Human Motion Estimation via Motion Compression and RefinementCode1
Deep Reinforcement Learning for Active Human Pose EstimationCode1
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the WildCode1
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the WildCode1
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose EstimationCode1
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose EstimationCode1
Cascaded deep monocular 3D human pose estimation with evolutionary training dataCode1
ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D PosesCode1
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose EstimationCode1
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion GenerationCode1
Anatomy-guided domain adaptation for 3D in-bed human pose estimationCode1
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human PoseCode1
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from VideoCode1
Combining Implicit Function Learning and Parametric Models for 3D Human ReconstructionCode1
Anatomy-aware 3D Human Pose Estimation with Bone-based Pose DecompositionCode1
Show:102550
← PrevPage 5 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