HyperAI

3D Human Pose Estimation On Humaneva I

Metriken

Mean Reconstruction Error (mm)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Mean Reconstruction Error (mm)
Paper TitleRepository
EDM26.93D Human Pose Estimation from a Single Image via Distance Matrix Regression-
Ours64Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
StridedTransformer (T=27 MRCNN)18.9Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
GLA-GCN (T=27, GT)9.2GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video
Occlusion-Aware Networks14.3Occlusion-Aware Networks for 3D Human Pose Estimation in Video-
DG-Net (T=4)19.5Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos-
DSRF40.3Depth sweep regression forests for estimating 3d human pose from images-
SMPLify (dense)74.5Unite the People: Closing the Loop Between 3D and 2D Human Representations
RTPCA19.1Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation
SMPLify79.9Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
MixSTE (T=43, FT)16.1MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
SIM (SH detections)24.6A simple yet effective baseline for 3d human pose estimation
Pose Grammar22.9Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation-
HEMlets Pose15.2HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation-
ConvFormer (T=43)24.3ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention
Sequence-to-sequence network22Exploiting temporal information for 3D pose estimation
Spatio-Temporal Network (T=128)13.53D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training-
Recurrent 3D Pose Sequence Machines30.8Recurrent 3D Pose Sequence Machines-
Attention (T=27 MA)15.4Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions-
DMHSR(J,B,D)33.7Deep Multitask Architecture for Integrated 2D and 3D Human Sensing-
0 of 31 row(s) selected.