AI Paper Atlas

Research map / 3D vision / Human pose estimation

EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere

Jiaxi Jiang, Paul Streli, Manuel Meier, Christian Holz

ECCV 2024 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 41 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 global motion decomposition (temporal + spatial normalization) instead of mean normalization (ablation)EgoPoser · AMASSMPJPE (cm): 6.25 -> 4.14Improved
retain vertical position (normalize only horizontal translation to head) (ablation)EgoPoser · AMASSMPJPE (cm): 4.96 -> 4.45Improved
add temporal normalization on top of spatial normalization (ablation)EgoPoser · AMASSMPJPE (cm): 4.45 -> 4.14Improved
use head-relative local input (improved versions) instead of global input for baselinesAvatarPoser · HPS BIB_EG_TourMPJPE (cm): 22.53 -> 11.48Improved
use head-relative local input (improved versions) for baseline on velocityAvatarPoser · HPS BIB_EG_TourMPJVE (cm/s): 60.25 -> 82.70Hurt
model FoV realistically instead of random hand masking (ablation)EgoPoser · AMASS FoV = 90 degMPJPE (cm): 14.84 -> 6.60Improved
add SlowFast fusion instead of 40-frame input (ablation)EgoPoser · AMASSMPJVE (cm/s): 28.12 -> 25.95Improved
SlowFast vs full 80-frame input (ablation)EgoPoser · AMASSMPJPE (cm): 4.11 -> 4.14No clear effect
estimate body shape jointly instead of using mean shape (ablation)EgoPoser · AMASS shape-awareMPJPE (cm): 6.36 -> 4.79Improved
shape data augmentation plus T-pose calibration instead of mean shape (ablation)EgoPoser · AMASS shape-awareMPJPE (cm): 6.36 -> 5.26Improved
global position input vs offset of origin up to 50 mAvatarPoser, AGRoL, AvatarJLM · AMASS with positional offsetposition errorHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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