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 126150 of 665 papers

TitleStatusHype
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose EstimationCode1
Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationCode1
HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDARCode1
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationCode1
P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose EstimationCode1
SmoothNet: A Plug-and-Play Network for Refining Human Poses in VideosCode1
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion GenerationCode1
ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D PosesCode1
GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic CamerasCode1
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-LearningCode1
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose EstimationCode1
A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human PoseCode1
Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online AdaptationCode1
Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View CamerasCode1
Leveraging MoCap Data for Human Mesh RecoveryCode1
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose EstimationCode1
Localization with Sampling-ArgmaxCode1
Learning to Regress Bodies from Images using Differentiable Semantic RenderingCode1
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the WildCode1
SPEC: Seeing People in the Wild with an Estimated CameraCode1
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose EstimationCode1
Probabilistic Modeling for Human Mesh RecoveryCode1
Sequential 3D Human Pose Estimation Using Adaptive Point Cloud Sampling StrategyCode1
DECA: Deep viewpoint-Equivariant human pose estimation using Capsule AutoencodersCode1
LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh RenderingCode1
Show:102550
← PrevPage 6 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