SOTAVerified

Monocular 3D Human Pose Estimation

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

Papers

Showing 125 of 101 papers

TitleStatusHype
MotionBERT: A Unified Perspective on Learning Human Motion RepresentationsCode3
ICON: Implicit Clothed humans Obtained from NormalsCode2
TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose EstimationCode2
PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space ModelCode2
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer NetworkCode2
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose EstimationCode2
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in VideoCode2
Double-chain Constraints for 3D Human Pose Estimation in Images and VideosCode1
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose EstimationCode1
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose ReconstructionCode1
3D Human Pose and Shape Estimation via HybrIK-TransformerCode1
Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose EstimationCode1
AGORA: Avatars in Geography Optimized for Regression AnalysisCode1
DiffPose: Toward More Reliable 3D Pose EstimationCode1
Cascaded deep monocular 3D human pose estimation with evolutionary training dataCode1
Capturing and Inferring Dense Full-Body Human-Scene ContactCode1
GFPose: Learning 3D Human Pose Prior with Gradient FieldsCode1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
DECA: Deep viewpoint-Equivariant human pose estimation using Capsule AutoencodersCode1
Anatomy-aware 3D Human Pose Estimation with Bone-based Pose DecompositionCode1
A simple yet effective baseline for 3d human pose estimationCode1
3D-LFM: Lifting Foundation ModelCode1
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the WildCode1
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.