AI Paper Atlas

Research map / 3D vision / Human pose estimation

PoseAnchor: Robust Root Position Estimation for 3D Human Pose Estimation

Jun-Hee Kim, Jumin Han, Seong-Whan Lee

ICCV 2025 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 7 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 direct root regression (Root+) to root-centered baseline (ablation)MixSTE · Human3.6MMPJPE: 40.9 -> 41.4Hurt
replace Root+ regression with zero-shot ITRR root estimation (ZS-anchor) (ablation)MixSTE · Human3.6MMRPE: 116.7 -> 100.5Improved
replace Root+ regression with zero-shot ITRR root estimation (ZS-anchor) (ablation)MixSTE · Human3.6MMPJPE: 41.4 -> 40.9No clear effect
add support-set-filtered training (PoseAnchor) to ZS-anchor (ablation)MixSTE · Human3.6MMPJPE: 40.9 -> 40.3Improved
add support-set-filtered training (PoseAnchor) to ZS-anchor (ablation)MixSTE · Human3.6MMRPE: 100.5 -> 96.7Improved
apply PoseAnchor instead of Root+Martinez et al. · Human3.6MMRPE: 146.7 -> 133.7Improved
apply PoseAnchor instead of Root+VPose · Human3.6MMRPE: 124.9 -> 112.0Improved
apply PoseAnchor instead of Root+GLA-GCN · Human3.6MMRPE: 119.2 -> 106.4Improved
use PoseAnchor instead of Root+ under 2D noise sigma=10 (ablation)MixSTE · Human3.6M GT 2D + noiseAbs-MPJPE: 524.7 -> 366.2Improved
use PoseAnchor instead of Root+ under 2D noise sigma=2 (ablation)MixSTE · Human3.6M GT 2D + noiseAbs-MPJPE: 117.4 -> 82.5Improved
use PoseAnchor instead of Root+ without noise (ablation)MixSTE · Human3.6M GT 2D + noiseAbs-MPJPE: 85.6 -> 82.2No clear effect
use ITRR support set to filter joints (ablation)ZS-anchor · Human3.6M2D detection error (pixels): 79.9 vs 13.1Improved

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