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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 451–500 of 665 papers

TitleStatusHype
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking—0
SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency—0
3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training—0
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network—0
Heuristic Weakly Supervised 3D Human Pose EstimationCode0
Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose DataCode0
3D Human Pose Regression using Graph Convolutional NetworkCode0
TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video—0
KAMA: 3D Keypoint Aware Body Mesh Articulation—0
Skeletor: Skeletal Transformers for Robust Body-Pose Estimation—0
Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective—0
Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting—0
SimPoE: Simulated Character Control for 3D Human Pose Estimation—0
Self-Attentive 3D Human Pose and Shape Estimation from Videos—0
Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild—0
PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos—0
Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions—0
On the role of depth predictions for 3D human pose estimation—0
PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation—0
Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation—0
SMPLy Benchmarking 3D Human Pose Estimation in the Wild—0
Towards Locality Similarity Preserving to 3D Human Pose Estimation—0
Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation—0
Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video—0
Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution—0
Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation—0
HPERL: 3D Human Pose Estimation from RGB and LiDARCode0
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization—0
Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation—0
A review of 3D human pose estimation algorithms for markerless motion capture—0
Beyond Weak Perspective for Monocular 3D Human Pose Estimation—0
SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regression—0
LiftFormer: 3D Human Pose Estimation using attention models—0
Human Body Model Fitting by Learned Gradient Descent—0
Neural Descent for Visual 3D Human Pose and Shape—0
Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose EstimationCode0
HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation—0
Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach—0
End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose Estimation—0
A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose EstimationCode0
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation—0
Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation—0
Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods—0
Deep Kinematics Analysis for Monocular 3D Human Pose Estimation—0
Object-Occluded Human Shape and Pose Estimation From a Single Color Image—0
PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation—0
3D human pose estimation with adaptive receptive fields and dilated temporal convolutions—0
Towards Generalization of 3D Human Pose Estimation In The Wild—0
Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video—0
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis—0
Show:102550
← PrevPage 10 of 14Next →
All datasets3DPWMPI-INF-3DHPHuman3.6MHumanEva-IH3WBTotal CaptureEMDBAGORAPanopticSurreal3D Poses in the Wild ChallengeAIST++

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Simple-baselinePA-MPJPE157—Unverified
2HMRMPJPE130—Unverified
3BMPMPVPE119.3—Unverified
4SPINMPVPE116.4—Unverified
5Wenshuo et a;.MPVPE112.6—Unverified
6TCMR (T=16 w/o 3DPW)MPVPE111.5—Unverified
7CHOMPMPVPE110.1—Unverified
8PC-HMRMPVPE108.6—Unverified
93DCrowdNetMPVPE108.5—Unverified
10SMPLifyPA-MPJPE106.8—Unverified
#ModelMetricClaimedVerifiedStatus
1VNect (Augm.)MPJPE124.7—Unverified
2HMRMPJPE124.2—Unverified
3Single-Shot Multi-PersonMPJPE122.2—Unverified
4MehtaMPJPE117.6—Unverified
5PONetMPJPE115—Unverified
6Pose Consensus (monocular)MPJPE112.1—Unverified
7GeoRep (fully-supervised)MPJPE110.8—Unverified
8XFormer (HRNet)MPJPE109.8—Unverified
9EpipolarPose (fully-supervised)MPJPE108.99—Unverified
10SPINMPJPE105.2—Unverified