AI Paper Atlas

Research map / 3D vision / Human pose estimation

Event-Based Non-rigid Reconstruction of Low-Rank Parametrized Deformations from Contours

Yuxuan Xue, Haolong Li, Stefan Leutenegger, Jörg Stückler

IJCV 2024 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 15 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
replace Nehvi's generative optimization with EM contour associationMANO hand tracking · Synthetic MANO handmean MPJPE (mm): 11.61 -> 4.52Improved
replace Nehvi's generative optimization with EM contour associationMANO hand tracking · Synthetic MANO handmedian MPJPE (mm): 10.85 -> 4.27Improved
replace Rudnev's learned network with EM contour optimizationSMPL-X hand tracking · Synthetic SMPL-X handmean MPJPE (mm): 11.88 -> 1.11Improved
replace Rudnev's learned network with EM contour optimizationSMPL-X hand tracking · Synthetic SMPL-X handmedian MPJPE (mm): 10.73 -> 0.76Improved
add elbow joint and smaller hand scale (arm & hand instead of hand only)EM contour method · Synthetic SMPL-Xmean MPJPE (mm): 1.11 -> 15.39Hurt
use hard data association with most likely face in E-step instead of soft (ablation)EM contour method · SupplementaryaccuracyNo clear effect
add longitudinal distance term to M-step likelihood (ablation)EM contour method · design choicelikelihoodHurt

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