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 151–200 of 665 papers

TitleStatusHype
Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling—0
PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose EstimationCode1
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent ConversationCode1
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh ReconstructionCode1
Double-chain Constraints for 3D Human Pose Estimation in Images and VideosCode1
Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor ScenesCode1
Iterative Graph Filtering Network for 3D Human Pose EstimationCode0
Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving—0
ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting—0
GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular VideoCode1
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose EstimationCode1
ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning—0
Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view—0
MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling—0
Representation learning of vertex heatmaps for 3D human mesh reconstruction from multi-view images—0
Automatic Labeling of Parkinson’s Disease Gait Videos with Weak SupervisionCode0
LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Network—0
EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors—0
Motion-DVAE: Unsupervised learning for fast human motion denoising—0
TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D EnvironmentsCode3
Humans in 4D: Reconstructing and Tracking Humans with TransformersCode3
Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training—0
XFormer: Fast and Accurate Monocular 3D Body Capture—0
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape EstimationCode2
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution EstimationCode1
Regular Splitting Graph Network for 3D Human Pose EstimationCode0
TAPE: Temporal Attention-based Probabilistic human pose and shape EstimationCode0
Interweaved Graph and Attention Network for 3D Human Pose EstimationCode1
Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation—0
Sampling is Matter: Point-guided 3D Human Mesh ReconstructionCode1
Human Pose Estimation in Monocular Omnidirectional Top-View Images—0
HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh RecoveryCode3
Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field RegistrationCode1
Self-supervised 3D Human Pose Estimation from a Single Image—0
ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional AttentionCode0
SportsPose -- A Dynamic 3D sports pose datasetCode1
3D Human Pose Estimation via Intuitive Physics—0
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose EstimationCode2
Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose EstimationCode1
One-Stage 3D Whole-Body Mesh Recovery with Component Aware TransformerCode2
Global-to-Local Modeling for Video-based 3D Human Pose and Shape EstimationCode1
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh ReconstructionCode1
A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual PerceptionCode1
DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos—0
POTTER: Pooling Attention Transformer for Efficient Human Mesh RecoveryCode1
BoPR: Body-aware Part Regressor for Human Shape and Pose EstimationCode0
3D Human Mesh Estimation from Virtual MarkersCode2
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis AggregationCode1
Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal TransformerCode1
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers—0
Show:102550
← PrevPage 4 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