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 201250 of 665 papers

TitleStatusHype
Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the WildCode1
Epipolar TransformersCode1
Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic DataCode1
Estimating Egocentric 3D Human Pose in Global SpaceCode1
Body Meshes as PointsCode1
AGORA: Avatars in Geography Optimized for Regression AnalysisCode1
Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion PriorCode1
EventEgo3D: 3D Human Motion Capture from Egocentric Event StreamsCode1
Lifting Monocular Events to 3D Human PosesCode1
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose EstimationCode1
GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image ReconstructionCode1
Live Stream Temporally Embedded 3D Human Body Pose and Shape EstimationCode1
Localization with Sampling-ArgmaxCode1
Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded PeopleCode1
Graph Stacked Hourglass Networks for 3D Human Pose EstimationCode1
MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose EstimationCode1
Context Modeling in 3D Human Pose Estimation: A Unified PerspectiveCode1
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular VideosCode1
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-LearningCode1
Mesh GraphormerCode1
MeshPose: Unifying DensePose and 3D Body Mesh reconstructionCode1
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic ProjectionCode1
Conditional Directed Graph Convolution for 3D Human Pose EstimationCode1
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose EstimationCode1
GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose EstimationCode1
FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion ReconstructionCode1
Human Pose Regression with Residual Log-likelihood EstimationCode1
FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World ConditionsCode1
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the WildCode1
On Self-Contact and Human PoseCode1
Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose EstimationCode1
Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric ApproachCode1
Compositional Human Pose RegressionCode0
Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributionsCode0
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape EstimationCode0
MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh ReconstructionCode0
Chirality Nets for Human Pose RegressionCode0
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action RecognitionCode0
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density NetworkCode0
2D/3D Pose Estimation and Action Recognition using Multitask Deep LearningCode0
Generalizing Monocular 3D Human Pose Estimation in the WildCode0
Monocular Total Capture: Posing Face, Body, and Hands in the WildCode0
Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose DataCode0
Can WiFi Estimate Person Pose?Code0
Flexible graph convolutional network for 3D human pose estimationCode0
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion CaptureCode0
Mirror-Aware Neural HumansCode0
Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose EstimationCode0
Camera Motion Agnostic 3D Human Pose EstimationCode0
Expressive Body Capture: 3D Hands, Face, and Body from a Single ImageCode0
Show:102550
← PrevPage 5 of 14Next →

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