AI Paper Atlas

Research map / 3D vision / Human pose estimation

Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation

Zhenbo Yu, Bingbing Ni, Jingwei Xu, Junjie Wang, Chenglong Zhao, Wenjun Zhang

ICCV 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 30 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 multi-view motion consistency loss Ltmc (ablation)lifting baseline · Human3.6M (GT 2D)PMPJPE: 46.0 -> 43.5Improved
add multi-view motion consistency loss Ltmc (ablation)lifting baseline · Human3.6M (GT 2D)MPJPE: 105.0 -> 101.7Improved
add KL scale distribution loss Lkl (ablation)lifting+Ltmc · Human3.6M (GT 2D)MPJPE: 101.7 -> 96.0Improved
add KL scale distribution loss Lkl (ablation)lifting+Ltmc · Human3.6M (GT 2D)PMPJPE: 43.5 -> 42.9Improved
add bone consistency loss Lbone (ablation)lifting+Ltmc+Lkl · Human3.6M (GT 2D)MPJPE: 96.0 -> 85.3Improved
add bone consistency loss Lbone (ablation)lifting+Ltmc+Lkl · Human3.6M (GT 2D)PMPJPE: 42.9 -> 42.0Improved
add scale estimation module on 2D pose (ablation)lifting with universal scale · Human3.6MMPJPE: 105.0 -> 85.3Improved
add scale estimation module on 2D pose (ablation)lifting with no normalization · Human3.6MMPJPE: 260.7 -> 233.4Improved
use universal scale normalization instead of step-wise (ablation)lifting · Human3.6MPMPJPE: 48.5 -> 46.0Improved
apply scale module on 2D input rather than 3D output (ablation)lifting · Human3.6MMPJPE: 97.5 -> 85.3Improved
apply scale module on 2D input rather than 3D output (ablation)lifting · Human3.6MPMPJPE: 43.6 -> 42.0Improved
feed reference scale from ground truth instead of learned scalelifting · Human3.6MPMPJPE: 42.0 -> 39.7Improved

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