| A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba | | 11.4 | SAMA-L (GT 2D, T=351, seq2seq) | 2025-07-26 |
| FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models | ✓ Link | 16.7 | FinePOSE + JPMA (GT 2D, T=243, H=20, K=10) | 2024-05-08 |
| MotionBERT: A Unified Perspective on Learning Human Motion Representations | ✓ Link | 16.9 | MotionBERT (GT 2D, T=243, finetuned) (extra data) | 2022-10-12 |
| MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network | ✓ Link | 17.3 | MotionAGFormer-L | 2023-10-25 |
| SemGAN: A Semantic and Hierarchical Adversarial Network for 3D Human Pose Estimation | | 18.8 | SemGAN (GT 2D, T=243) | 2026-09-08 |
| DiffPose: Toward More Reliable 3D Pose Estimation | ✓ Link | 18.9 | DiffPose GMM-Diff M=5 (GT 2D, T=243, mean N=5) | 2022-11-30 |
| KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation | ✓ Link | 19.0 | KTPFormer (GT 2D, T=243) | 2024-03-31 |
| Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation | ✓ Link | 19.6 | D3DP + JPMA (N=243, H=20, K=10) | 2023-03-21 |
| SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistency | | 20.0 | SEAL-pose (Graph) + MixSTE (GT 2D, T=243) | 2026-02-23 |
| SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation | | 20.92 | SasMamba-large (GT 2D, T=243, seq2seq) | 2025-11-12 |
| GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video | ✓ Link | 21.0 | GLA-GCN (GT 2D, T=243, C_out=512, sequence reconstruction) | 2023-07-12 |
| MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video | ✓ Link | 21.6 | MixSTE (GT 2D, T=243) | 2022-03-02 |
| MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling | | 27.2 | MPM (GT 2D, T=243) (extra data) | 2023-06-29 |
| HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation | ✓ Link | 28.1 | HyperDiff + JPMA (GT 2D, T=1, H=10, K=5) | 2025-08-20 |
| HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation | | 28.3 | HiPART | 2025-03-30 |
| P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation | ✓ Link | 29.3 | P-STMO-S (243 frames) | 2022-03-15 |
| MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation | ✓ Link | 30.5 | MHFormer (GT 2D, T=351) | 2021-11-24 |
| Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation | ✓ Link | 31.0 | DiffPyramid (GT 2D, T=1, mean N=5) | 2025-06-03 |
| 3D Human Pose Estimation with Spatial and Temporal Transformers | ✓ Link | 31.3 | PoseFormer | 2021-03-18 |
| Interweaved Graph and Attention Network for 3D Human Pose Estimation | ✓ Link | 32.7 | IGANet (GT 2D, T=1) | 2023-04-27 |
| Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation | ✓ Link | 32.7 | GUMLP + UAO (GT 2D, T=1) | 2024-02-04 |
| Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation | ✓ Link | 33.51 | PoseKAN | 2025-11-11 |
| 3D human pose estimation in video with temporal convolutions and semi-supervised training | ✓ Link | 37.2 | VideoPose3D (243 frames) | 2018-11-28 |
| A simple yet effective baseline for 3d human pose estimation | ✓ Link | 45.5 | Martinez Baseline | 2017-05-08 |