DeepFuse-IMU

Reported on 4 benchmarks across 4 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

3D Human Pose EstimationonTotal Capture
Average MPJPE (mm)· 2019-12-09
28.9
best: 112 (ROS node wrapping)
DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image arXiv:1912.04071
Pose EstimationonTotal Capture
Average MPJPE (mm)· 2019-12-09
28.9
best: 112 (ROS node wrapping)
DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image arXiv:1912.04071

Methodology1 result

3DonTotal Capture
Average MPJPE (mm)· 2019-12-09
28.9
best: 112 (ROS node wrapping)
DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image arXiv:1912.04071

Audio1 result

1 Image, 2*2 StitchionTotal Capture
Average MPJPE (mm)· 2019-12-09
28.9
best: 112 (ROS node wrapping)
DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image arXiv:1912.04071