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 126150 of 665 papers

TitleStatusHype
Compressed Volumetric Heatmaps for Multi-Person 3D Pose EstimationCode1
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
Human Pose Regression with Residual Log-likelihood EstimationCode1
3D Human Pose and Shape Estimation via HybrIK-TransformerCode1
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose EstimaitonCode1
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor ScenesCode1
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationCode1
Double-chain Constraints for 3D Human Pose Estimation in Images and VideosCode1
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion PredictionCode1
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution EstimationCode1
Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted SensorsCode1
D&D: Learning Human Dynamics from Dynamic CameraCode1
DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose EstimationCode1
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the WildCode1
A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human PoseCode1
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh ReconstructionCode1
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose EstimationCode1
DECA: Deep viewpoint-Equivariant human pose estimation using Capsule AutoencodersCode1
HDFormer: High-order Directed Transformer for 3D Human Pose EstimationCode1
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with TransformersCode1
Anatomy-aware 3D Human Pose Estimation with Bone-based Pose DecompositionCode1
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis AggregationCode1
Anatomy-guided domain adaptation for 3D in-bed human pose estimationCode1
A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual PerceptionCode1
Show:102550
← PrevPage 6 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