HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

3D Human Pose Estimation On Total Capture

Metrics

Average MPJPE (mm)

Results

Performance results of various models on this benchmark

Model Name
Average MPJPE (mm)
Paper TitleRepository
IMUPVH70Total capture: 3D human pose estimation fusing video and inertial sensors-
MTF-Transformer (M=0.4, T=7)29.2Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation-
AdaFuse19.2AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
AutoEnc35Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling-
LWCDR27.5Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation-
PVH107Total capture: 3D human pose estimation fusing video and inertial sensors-
Tri-CPM99Convolutional Pose Machines
DeepFuse-IMU28.9DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image-
AdaDeepFuse22.5FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation-
ROS node wrapping1123D Human Pose Estimation in RGBD Images for Robotic Task Learning
Fusion-RPSM29.0Cross View Fusion for 3D Human Pose Estimation
Single-RPSM41.0Cross View Fusion for 3D Human Pose Estimation
GeoFuse24.6Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach
DeepFuse-Vision Only32.7DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image-
0 of 14 row(s) selected.