AI Paper Atlas

Research map / 3D vision / Human pose estimation

EM-POSE: 3D Human Pose Estimation From Sparse Electromagnetic Trackers

Manuel Kaufmann, Yi Zhao, Chengcheng Tang, Lingling Tao, Christopher Twigg, Jie Song, Robert Wang, Otmar Hilliges

ICCV 2021 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 45 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add subject-specific rotational and translational sensor offsets in training (ablation)Ours 12 · EM-POSE real test set (subjects 1-4)MPJPE: 167.6 -> 31.8Improved
add subject-specific translational offsets t in training (ablation)Ours 12 · EM-POSE real test set (subjects 1-4)MPJPE: 35.6 -> 31.8Improved
add position measurements to orientation-only input (ablation)Ours 12 · EM-POSE real test set (subjects 1-4)MPJPE: 50.8 -> 31.8Improved
add orientation measurements to position-only input (ablation)Ours 12 · EM-POSE real test set (subjects 1-4)MPJAE: 16.2 -> 13.3Improved
add RNN providing the initial estimate to LGD (ablation)Ours 12 · EM-POSE real test set (subjects 1-4)MPJPE: 36.9 -> 31.8Improved
replace BiRNN regression with LGD RNN hybrid, 12 sensorspure learning baseline · EM-POSE real test set (subjects 1-4)MPJPE: 37.3 -> 31.8Improved
replace BiRNN regression with LGD RNN hybrid, 6 sensorspure learning baseline · EM-POSE real test set (subjects 1-4)MPJPE: 36.3 -> 35.4Improved
use temporal BiRNN instead of frame-wise ResNet, 12 sensorslearning baseline · EM-POSE real test set (subjects 1-4)MPJPE: 41.5 -> 37.3Improved
use 12 sensors instead of 6Ours (LGD RNN) · EM-POSE real test set (subjects 1-4)MPJPE: 35.4 -> 31.8Improved
add orientations and subject offsets to MoSh++-style optimizationoptimization baseline · EM-POSE real test set (subjects 1-4)MPJPE: 56.9 -> 44.2Improved
replace pure optimization with learned gradient descentpos + ori 12 · EM-POSE real test set (subjects 1-4)MPJPE: 44.2 -> 31.8Improved
replace BiRNN with LGD RNN on unseen subject, 12 sensorspure learning baseline · EM-POSE real test set (subject 5, cross-subject)MPJPE: 40.7 -> 32.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy