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

English

Unsupervised 3D Human Pose Estimation On

Metrics

MPJPE

N-MPJPE

P-MPJPE

Results

Performance results of various models on this benchmark

Model Name	MPJPE	N-MPJPE	P-MPJPE	Paper Title	Repository
Mask as Supervision	95.9	96.8	90.4	Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Kinematic-Structure-Preserved Representation	-	-	-	Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation	-
HDVR	82.1	-	-	Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition
PGNIS	99.2	-	-	Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis	-
CHOMP	64.7	-	-	Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior
Non-Local Latent Relation Distillation	97.8	-	-	Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation	-
ElePose	64.0	-	-	ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses
SVMAC	98.3	-	-	SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency	-
Uncertainty-Aware Adaptation	103.2	-	-	Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation	-
LInKs	-	61.6	-	LInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation	-
CLIFF (HR-W48)	-	-	-	CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
ITES-TS	85.3	-	59.8	Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

0 of 12 row(s) selected.