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 76100 of 665 papers

TitleStatusHype
Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised TrainingCode0
Hybrid 3D Human Pose Estimation with Monocular Video and Sparse IMUs0
TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose RepresentationCode3
3D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN RefinementCode0
UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues0
SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose EstimationCode2
SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers0
EventEgo3D: 3D Human Motion Capture from Egocentric Event StreamsCode1
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose EstimationCode2
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose EstimationCode1
A Survey on 3D Egocentric Human Pose EstimationCode2
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild VideosCode4
GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image ReconstructionCode1
Exploring 3D Human Pose Estimation and Forecasting from the Robot's Perspective: The HARPER Dataset0
Self-learning Canonical Space for Multi-view 3D Human Pose Estimation0
PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery0
A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose EstimationCode1
3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models0
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Deep learning for 3D human pose estimation and mesh recovery: A surveyCode2
NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye ImagesCode0
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single ShotCode3
Occlusion Resilient 3D Human Pose Estimation0
Lester: rotoscope animation through video object segmentation and trackingCode1
Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation0
Show:102550
← PrevPage 4 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