HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

3D Human Pose Estimation On Human36M

评估指标

Average MPJPE (mm)
PA-MPJPE

评测结果

各个模型在此基准测试上的表现结果

Paper Title
Pyramid of 3D HOG features125.28-Predicting people’s 3D poses from short sequences
Structured Prediction125.0-Structured Prediction of 3D Human Pose with Deep Neural Networks
StructNet-Avg(500)-APF121.31-Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation
3DCNN119-Human Pose Estimation in Space and Time using 3D CNN
CNN Lifter117.34-3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
Events116.4-Lifting Monocular Events to 3D Human Poses
Sparseness Meets Deepness113.01-Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
Deep Kinematic Pose107.26-Deep Kinematic Pose Regression
Embodied Scene-aware103.473.7Embodied Scene-aware Human Pose Estimation
Dual-source approach97.39108.3A Dual-Source Approach for 3D Pose Estimation from a Single Image
CHPR92.467.5Compositional Human Pose Regression
HUND (SS)91.866Neural Descent for Visual 3D Human Pose and Shape
RepNet89.9-RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
Projected-pose belief maps + 2D fusion layers88.39-Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
HMR87.9758.1End-to-end Recovery of Human Shape and Pose
LCR-Net87.771.6LCR-Net: Localization-Classification-Regression for Human Pose
THUNDR (WS)8762.2THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
Ray3D (T=9 CPN H36M+HEva+3DHP)84.4-Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization
HUND+SO+GT + Dynamics8456Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video
HMMR (T=20)83.756.9Learning 3D Human Dynamics from Video
0 of 357 row(s) selected.