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 251–300 of 665 papers

TitleStatusHype
AMPose: Alternately Mixed Global-Local Attention Model for 3D Human Pose EstimationCode0
(Fusionformer):Exploiting the Joint Motion Synergy with Fusion Network Based On Transformer for 3D Human Pose Estimation—0
Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from VideosCode0
Decanus to Legatus: Synthetic training for 2D-3D human pose liftingCode0
D&D: Learning Human Dynamics from Dynamic CameraCode1
PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationCode1
Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation—0
FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation—0
Learnable human mesh triangulation for 3D human pose and shape estimation—0
MoCapDeform: Monocular 3D Human Motion Capture in Deformable ScenesCode1
Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose EstimationCode1
IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation—0
UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture—0
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape EstimationCode0
Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation—0
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with TransformersCode1
KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints—0
Live Stream Temporally Embedded 3D Human Body Pose and Shape EstimationCode1
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic ProjectionCode1
Dynamic Graph Reasoning for Multi-person 3D Pose Estimation—0
DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose EstimationCode1
Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent AnnotationsCode0
Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation—0
PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular ImagesCode2
Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion PriorCode1
Learning to Estimate External Forces of Human Motion in VideoCode1
Multi-person 3D pose estimation from a single image captured by a fisheye camera—0
PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning—0
BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation—0
Embodied Scene-aware Human Pose Estimation—0
GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose EstimationCode1
Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation—0
Efficient Human Pose Estimation via 3D Event Point CloudCode1
SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space—0
FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERCode0
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose—0
VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation—0
Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video—0
Differentiable Dynamics for Articulated 3d Human Motion Reconstruction—0
"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation—0
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation—0
PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimationCode1
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering TransformerCode2
Integrated In-vehicle Monitoring System Using 3D Human Pose Estimation and Seat Belt Segmentation—0
3D Human Pose Estimation for Free-from and Moving Activities Using WiFi—0
Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation—0
Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery—0
Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation—0
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisionCode2
Show:102550
← PrevPage 6 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