HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Multi Hypotheses 3D Human Pose Estimation On

Metrics

Average MPJPE (mm)
Average PMPJPE (mm)
Using 2D ground-truth joints

Results

Performance results of various models on this benchmark

Model Name
Average MPJPE (mm)
Average PMPJPE (mm)
Using 2D ground-truth joints
Paper TitleRepository
GFPose (HPJ2D-000, S=200)35.630.516.9GFPose: Learning 3D Human Pose Prior with Gradient Fields
Li et al.73.944.3-Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses
cGNF xlarge w Lsample48.5--Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
MDN52.742.6-Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
D3DP35.4-NoDiffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Sharma et al.46.837.3-Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
GraphMDN46.236.3-GraphMDN: Leveraging graph structure and deep learning to solve inverse problems-
MHEntropy-36.8-MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery-
GFPose (HPJ2D-010, S=200)35.1--GFPose: Learning 3D Human Pose Prior with Gradient Fields
cGNF w Lsample53--Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
0 of 10 row(s) selected.