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 201225 of 665 papers

TitleStatusHype
Conditional Directed Graph Convolution for 3D Human Pose EstimationCode1
Epipolar TransformersCode1
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose EstimationCode1
Estimating Egocentric 3D Human Pose in Global SpaceCode1
Body Meshes as PointsCode1
FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion ReconstructionCode1
Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal TransformerCode1
EventEgo3D: 3D Human Motion Capture from Egocentric Event StreamsCode1
Learning to Estimate External Forces of Human Motion in VideoCode1
LiDAR-HMR: 3D Human Mesh Recovery from LiDARCode1
Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose EstimationCode1
Scene-aware Egocentric 3D Human Pose EstimationCode1
Self-supervision on Unlabelled OR Data for Multi-person 2D/3D Human Pose EstimationCode1
Semantic Graph Convolutional Networks for 3D Human Pose RegressionCode1
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the LoopCode1
Leveraging MoCap Data for Human Mesh RecoveryCode1
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose EstimationCode1
Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field RegistrationCode1
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-LearningCode1
Learning to Regress Bodies from Images using Differentiable Semantic RenderingCode1
Lester: rotoscope animation through video object segmentation and trackingCode1
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic ProjectionCode1
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and RefinementCode1
PARE: Part Attention Regressor for 3D Human Body EstimationCode1
Probabilistic Modeling for Human Mesh RecoveryCode1
Show:102550
← PrevPage 9 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