3D Human Pose Estimation On Humaneva I

المقاييس

Mean Reconstruction Error (mm)

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

		Paper Title
SMPLify	79.9	Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
SMPLify (dense)	74.5	Unite the People: Closing the Loop Between 3D and 2D Human Representations
Wang et al.	71.3	Robust Estimation of 3D Human Poses from a Single Image
Ours	64	Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
Simo-Serra et al.	56.7	A Joint Model for 2D and 3D Pose Estimation from a Single Image
DSRF	40.3	Depth sweep regression forests for estimating 3d human pose from images
TGP	39.1	Twin gaussian processes for structured prediction
Dual-source approach	38.9	A Dual-Source Approach for 3D Pose Estimation from a Single Image
DMHSR(J,B,D)	33.7	Deep Multitask Architecture for Integrated 2D and 3D Human Sensing
Recurrent 3D Pose Sequence Machines	30.8	Recurrent 3D Pose Sequence Machines
EDM	26.9	3D Human Pose Estimation from a Single Image via Distance Matrix Regression
SIM (SH detections)	24.6	A simple yet effective baseline for 3d human pose estimation
ConvFormer (T=43)	24.3	ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention
c2f-vol	24.3	Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
Ours (Oracle)	23.9	Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
Pose Grammar	22.9	Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation
3D Pose Grammar Network	22.9	Learning Pose Grammar for Monocular 3D Pose Estimation
Sequence-to-sequence network	22	Exploiting temporal information for 3D pose estimation
PoseFormer	21.6	3D Human Pose Estimation with Spatial and Temporal Transformers
GAST	21.2	A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video

0 of 31 row(s) selected.

Command Palette

3D Human Pose Estimation On Humaneva I

المقاييس

النتائج