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 626650 of 665 papers

TitleStatusHype
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing0
A Multi-view RGB-D Approach for Human Pose Estimation in Operating RoomsCode0
Unite the People: Closing the Loop Between 3D and 2D Human RepresentationsCode0
Learning from Synthetic HumansCode0
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImageCode0
3D Human Pose Estimation = 2D Pose Estimation + Matching0
Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision0
3D Human Pose Estimation from a Single Image via Distance Matrix Regression0
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human PoseCode1
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose EstimationCode0
Deep Kinematic Pose Regression0
Human Pose Estimation in Space and Time using 3D CNN0
3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information0
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single ImageCode1
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild0
Structured Prediction of 3D Human Pose with Deep Neural Networks0
Fusing Audio, Textual and Visual Features for Sentiment Analysis of News Videos0
Towards Viewpoint Invariant 3D Human Pose EstimationCode0
Convolutional Pose MachinesCode0
Understanding Human-Centric Images: From Geometry to Fashion0
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular VideoCode0
Direct Prediction of 3D Body Poses from Motion Compensated Sequences0
A Dual-Source Approach for 3D Pose Estimation from a Single Image0
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach0
Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation0
Show:102550
← PrevPage 26 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