Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Multi Hypotheses 3D Human Pose Estimation On 2

Metrics

Best-Hypothesis MPJPE (n = 25)

Best-Hypothesis PMPJPE (n = 25)

H36M PMPJPE (n = 1)

H36M PMPJPE (n = 25)

Most-Likely Hypothesis PMPJPE (n = 1)

Results

Performance results of various models on this benchmark

Model Name	Best-Hypothesis MPJPE (n = 25)	Best-Hypothesis PMPJPE (n = 25)	H36M PMPJPE (n = 1)	H36M PMPJPE (n = 25)	Most-Likely Hypothesis PMPJPE (n = 1)	Paper Title	Repository
ProHMR	-	60.1	41.2	36.8	67.3	Probabilistic Modeling for Human Mesh Recovery
SMPL-MDN (by 3D Multi-bodies)	91.5	69.5	44.8	42.7	74.7	Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
ProHMR (2D Vis, by MHEntropy)	-	82.6	-	64.3	-	Probabilistic Modeling for Human Mesh Recovery
HuManiFlow	-	-	-	-	-	HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation
3D Multi-bodies	90.0	64.2	41.6	42.2	67.8	3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data	-
MHEntropy (3D)	-	50.6	-	36.8	-	MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery	-
SMPL-CVAE	109.7	75.1	46.7	46.2	76.5	3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data	-
HMR	-	-	56.8	56.8	-	End-to-end Recovery of Human Shape and Pose
MHEntropy (2D Vis)	-	66.4	-	51.3	-	MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery	-
HMR (2D Vis, by MHEntropy)	-	85.2	67.4	67.4	85.2	End-to-end Recovery of Human Shape and Pose

0 of 10 row(s) selected.