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 151200 of 665 papers

TitleStatusHype
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh ReconstructionCode1
FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World ConditionsCode1
Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose EstimationCode1
Making DensePose fast and lightCode1
LiDAR-HMR: 3D Human Mesh Recovery from LiDARCode1
Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion CaptureCode1
Deep Reinforcement Learning for Active Human Pose EstimationCode1
A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in VideoCode1
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose EstimationCode1
Lifting Monocular Events to 3D Human PosesCode1
Deformable Mesh Transformer for 3D Human Mesh RecoveryCode1
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from VideosCode1
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with TransformersCode1
A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual PerceptionCode1
EventEgo3D: 3D Human Motion Capture from Egocentric Event StreamsCode1
Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose EstimationCode1
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose EstimationCode1
MEEV: Body Mesh Estimation On Egocentric VideoCode1
Learning to Regress Bodies from Images using Differentiable Semantic RenderingCode1
Graph Stacked Hourglass Networks for 3D Human Pose EstimationCode1
Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose ReconstructionCode1
DiffPose: Toward More Reliable 3D Pose EstimationCode1
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View GeometryCode1
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis AggregationCode1
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose EstimaitonCode1
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent ConversationCode1
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Double-chain Constraints for 3D Human Pose Estimation in Images and VideosCode1
AGORA: Avatars in Geography Optimized for Regression AnalysisCode1
Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion PriorCode1
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Lester: rotoscope animation through video object segmentation and trackingCode1
Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View CamerasCode1
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion PredictionCode1
Efficient Domain Adaptation via Generative Prior for 3D Infant Pose EstimationCode1
Efficient Human Pose Estimation via 3D Event Point CloudCode1
Estimating Egocentric 3D Human Pose in Global SpaceCode1
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
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the LoopCode1
Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body ShapesCode1
EM-POSE: 3D Human Pose Estimation From Sparse Electromagnetic TrackersCode1
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose EstimationCode1
Context Modeling in 3D Human Pose Estimation: A Unified PerspectiveCode1
VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild EnvironmentCode1
Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal TransformerCode1
BLAPose: Enhancing 3D Human Pose Estimation with Bone Length AdjustmentCode1
GFPose: Learning 3D Human Pose Prior with Gradient FieldsCode1
Conditional Directed Graph Convolution for 3D Human Pose EstimationCode1
Show:102550
← PrevPage 4 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