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 551575 of 665 papers

TitleStatusHype
Resolving 3D Human Pose Ambiguities with 3D Scene ConstraintsCode0
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose EstimationCode0
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImageCode0
Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion CaptureCode0
Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributionsCode0
TAPE: Temporal Attention-based Probabilistic human pose and shape EstimationCode0
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion CaptureCode0
Unsupervised Geometry-Aware Representation for 3D Human Pose EstimationCode0
STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose EstimationCode0
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose EstimationCode0
3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware TransformerCode0
Cross View Fusion for 3D Human Pose EstimationCode0
Learning Temporal 3D Human Pose Estimation with Pseudo-LabelsCode0
Learning Skeletal Graph Neural Networks for Hard 3D Pose EstimationCode0
Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge NetworksCode0
Learning Pyramid-structured Long-range Dependencies for 3D Human Pose EstimationCode0
SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose EstimationCode0
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action RecognitionCode0
Convolutional Pose MachinesCode0
3D human pose estimation from depth maps using a deep combination of posesCode0
Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose EstimationCode0
ACRNet: Attention Cube Regression Network for Multi-view Real-time 3D Human Pose Estimation in TelemedicineCode0
MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose EstimationCode0
3D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN RefinementCode0
NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose EstimationCode0
Show:102550
← PrevPage 23 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