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 476500 of 665 papers

TitleStatusHype
Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation0
HPERL: 3D Human Pose Estimation from RGB and LiDARCode0
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization0
Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation0
A review of 3D human pose estimation algorithms for markerless motion capture0
Beyond Weak Perspective for Monocular 3D Human Pose Estimation0
SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regression0
LiftFormer: 3D Human Pose Estimation using attention models0
Human Body Model Fitting by Learned Gradient Descent0
Neural Descent for Visual 3D Human Pose and Shape0
Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose EstimationCode0
HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation0
Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach0
End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose Estimation0
A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose EstimationCode0
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation0
Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation0
Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods0
Deep Kinematics Analysis for Monocular 3D Human Pose Estimation0
Object-Occluded Human Shape and Pose Estimation From a Single Color Image0
PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation0
3D human pose estimation with adaptive receptive fields and dilated temporal convolutions0
Towards Generalization of 3D Human Pose Estimation In The Wild0
Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video0
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis0
Show:102550
← PrevPage 20 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