AI Paper Atlas

Research map / 3D vision / Human pose estimation

EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR

Zhenyu Li, Sai Kumar Dwivedi, Filip Maric, Carlos Chacón, Nadine Bertsch, Filippo Arcadu, Tomas Hodan, Michael Ramamonjisoa, Peter Wonka, Amy Zhao, Robin Kips, Cem Keskin and 2 more

CVPR 2026 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 1 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
predict pose parameters with forward kinematics instead of direct keypoint head (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.35 -> 4.17Improved
add causal temporal attention (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.35 -> 4.17Improved
add projected 2D keypoint conditioning in refinement (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.30 -> 4.17Improved
condition query on auxiliary metadata (headset pose) (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.39 -> 4.17Improved
add per-joint uncertainty head (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.25 -> 4.17Improved
add auto-labeling system (pseudo-labels from 70M unlabeled frames) (ablation)EPFv2 · EgoBody3Mwrist MPJPE (cm): 5.74 -> 5.07Improved
add auto-labeling system (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.17 -> 4.08Improved
add uncertainty distillation loss to ALS (ablation)EPFv2 · EgoBody3Moverall MPJPE (cm): 4.08 -> 4.02Improved
EPFv2 vs EgoPoseFormer on temporal smoothnessEPFv2 · EgoBody3MMPJVE: 0.87 -> 0.42Improved
EPFv2 w/o ALS vs Egobody3M on temporal smoothnessEPFv2 w/o ALS · EgoBody3MMPJVE: 0.54 -> 0.42Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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