3D Human Pose Estimation On Humaneva I

评估指标

Mean Reconstruction Error (mm)

评测结果

各个模型在此基准测试上的表现结果

模型名称	Mean Reconstruction Error (mm)	Paper Title	Repository
EDM	26.9	3D Human Pose Estimation from a Single Image via Distance Matrix Regression	-
Ours	64	Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
StridedTransformer (T=27 MRCNN)	18.9	Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
GLA-GCN (T=27, GT)	9.2	GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video
Occlusion-Aware Networks	14.3	Occlusion-Aware Networks for 3D Human Pose Estimation in Video	-
DG-Net (T=4)	19.5	Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos	-
DSRF	40.3	Depth sweep regression forests for estimating 3d human pose from images	-
SMPLify (dense)	74.5	Unite the People: Closing the Loop Between 3D and 2D Human Representations
RTPCA	19.1	Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation
SMPLify	79.9	Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
MixSTE (T=43, FT)	16.1	MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
SIM (SH detections)	24.6	A simple yet effective baseline for 3d human pose estimation
Pose Grammar	22.9	Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation	-
HEMlets Pose	15.2	HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 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
Sequence-to-sequence network	22	Exploiting temporal information for 3D pose estimation
Spatio-Temporal Network (T=128)	13.5	3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training	-
Recurrent 3D Pose Sequence Machines	30.8	Recurrent 3D Pose Sequence Machines	-
Attention (T=27 MA)	15.4	Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions	-
DMHSR(J,B,D)	33.7	Deep Multitask Architecture for Integrated 2D and 3D Human Sensing	-

0 of 31 row(s) selected.