SOTAVerified

Monocular 3D Human Pose Estimation

This task targets at 3D human pose estimation with a single RGB camera.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 101 papers

TitleStatusHype
Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images—0
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose EstimationCode0
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose EstimationCode0
TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose EstimationCode2
GenHMR: Generative Human Mesh Recovery—0
PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space ModelCode2
Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation—0
Di^2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation—0
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose EstimationCode2
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion FrameworkCode0
3D-LFM: Lifting Foundation ModelCode1
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose EstimationCode0
Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency—0
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer NetworkCode2
Double-chain Constraints for 3D Human Pose Estimation in Images and VideosCode1
Sampling is Matter: Point-guided 3D Human Mesh ReconstructionCode1
Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field RegistrationCode1
ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional AttentionCode0
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis AggregationCode1
3D Human Pose and Shape Estimation via HybrIK-TransformerCode1
CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations—0
GFPose: Learning 3D Human Pose Prior with Gradient FieldsCode1
DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic ModelCode0
DiffPose: Toward More Reliable 3D Pose EstimationCode1
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.