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 226250 of 665 papers

TitleStatusHype
Scene-aware Egocentric 3D Human Pose EstimationCode1
GFPose: Learning 3D Human Pose Prior with Gradient FieldsCode1
HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving0
DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic ModelCode0
DiffPose: Toward More Reliable 3D Pose EstimationCode1
Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in VideosCode1
DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models0
H3WB: Human3.6M 3D WholeBody Dataset and BenchmarkCode2
MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh ReconstructionCode0
Unsupervised 3D Keypoint Discovery with Multi-View Geometry0
Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge0
Anatomy-guided domain adaptation for 3D in-bed human pose estimationCode1
PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body EstimationCode0
MogaNet: Multi-order Gated Aggregation NetworkCode2
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and RefinementCode1
MEEV: Body Mesh Estimation On Egocentric VideoCode1
BlanketGen - A synthetic blanket occlusion augmentation pipeline for MoCap datasets0
3D Human Pose Estimation in Multi-View Operating Room Videos Using Differentiable Camera Projections0
Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributionsCode0
A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation0
mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors0
MotionBERT: A Unified Perspective on Learning Human Motion RepresentationsCode3
Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting TransformersCode1
ACRNet: Attention Cube Regression Network for Multi-view Real-time 3D Human Pose Estimation in TelemedicineCode0
Self-Supervised 3D Human Pose Estimation in Static Video Via Neural Rendering0
Show:102550
← PrevPage 10 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