3D Human Pose Estimation On Mpi Inf 3Dhp

Métriques

MPJPE

PCK

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	MPJPE	PCK	Paper Title	Repository
CanonPose	104	77	CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
Adversarial Learning	-	69.0	3D Human Pose Estimation in the Wild by Adversarial Learning	-
STR	95.3	-	Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos	-
Graph Stacked Hourglass Network	-	80.1	Graph Stacked Hourglass Networks for 3D Human Pose Estimation
DST-VIBE	93.4	-	Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation	-
MixSTE (T=27)	54.9	94.4	MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
Probabilistic Monocular	-	84.3	Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows
Self-Attentive	94.3	90.1	Self-Attentive 3D Human Pose and Shape Estimation from Videos	-
PONet	115.0	76.1	PONet: Robust 3D Human Pose Estimation via Learning Orientations Only	-
PoseTriplet	79.5	89.1	PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
CrossFormer	76.3	89.1	CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation
GeoRep (fully-supervised)	110.8	80.2	Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild	-
SRNET	-	77.6	SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach
RepNet (H36M)	92.5	81.8	RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
PoseLifter	-	84	PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose
PoseFormer (9 frames)	77.1	88.6	3D Human Pose Estimation with Spatial and Temporal Transformers
STCFormer (T=81)	23.1	98.7	3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention
W-HMR	83.2	-	W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration
Fusionformer (f=9)	28.2	97.9	(Fusionformer):Exploiting the Joint Motion Synergy with Fusion Network Based On Transformer for 3D Human Pose Estimation	-
FinePOSE	26.2	98.9	FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models	-

0 of 116 row(s) selected.