AI Paper Atlas

Research map / 3D vision / Human pose estimation

GLAMR: Global Occlusion-Aware Human Mesh Recovery With Dynamic Cameras

Ye Yuan, Umar Iqbal, Pavlo Molchanov, Kris Kitani, Jan Kautz

CVPR 2022 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 123 citations (OpenAlex)

Check 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
use GLAMR global reconstruction instead of KAMA with linear interpolationKAMA-based recovery · Dynamic Human3.6MG-MPJPE: 1735.2 -> 806.2Improved
use GLAMR motion infiller instead of ConvAEmotion infilling · AMASS testFID sampled: 31.4 -> 16.7Improved
replace LSTMs with Transformers (ablation)GLAMR trajectory predictor · AMASS testG-MPJPE: 466.9 -> 660.1Hurt
predict global 6-DoF trajectory directly instead of egocentric trajectory (ablation)GLAMR trajectory predictor · AMASS testG-MPJPE: 466.9 -> 763.0Hurt
use the global trajectory predictor rather than OpenSfM-derived global trajectories (ablation)GLAMR global optimization · Dynamic Human3.6MG-MPJPE: 1750.8 -> 806.2Improved
optimize egocentric trajectory instead of the 6-DoF root trajectory directly (ablation)GLAMR global optimization · Dynamic Human3.6MG-MPJPE: 877.3 -> 806.2Improved
add global optimization (ablation)GLAMR · 3DPW testRelative Translation Error: 1.92 -> 0.66Improved

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