AI Paper Atlas

Research map / 3D vision / Human pose estimation

Egocentric Pose Estimation From Human Vision Span

Hao Jiang, Vamsi Krishna Ithapu

ICCV 2021 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 33 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 Stage 2 3D pose refinement (ablation)Stage 1 egopose model · Synthetic data (60 test sequences)3D keypoint error (cm): 12.53 -> 11.76Improved
add shape features to motion features (ablation)MotionOnly · Synthetic data (60 test sequences)3D keypoint error (cm): 14.55 -> 11.76Improved
add motion history features to shape features (ablation)ShapeOnly · Synthetic data (60 test sequences)3D keypoint error (cm): 13.89 -> 11.76Improved
add camera height to the motion history image (ablation)NoHeight · Synthetic data (60 test sequences)3D keypoint error (cm): 14.52 -> 11.76Improved
add camera height to the motion history image (ablation)NoHeight · Synthetic data (60 test sequences)head orientation vector 1 error (deg): 13.01 -> 11.26Improved
use body shape input instead of hand keypoint map (ablation)HandMap · Synthetic data (60 test sequences)3D keypoint error (cm): 26.10 -> 11.76Improved
use non-recurrent network instead of RNN in Stage 1 (ablation)Stage1 (RNN variant) · Synthetic data (60 test sequences)3D keypoint error (cm): 12.52 -> 12.53No clear effect
use non-recurrent network instead of RNN with refinement (ablation)Full model vs RNN variant · Synthetic data (60 test sequences)3D keypoint error (cm): 11.76Improved
add Stage 2 refinement (head pose unchanged) (ablation)Stage 1 model · Synthetic data (60 test sequences)head orientation vector 1 error (deg): 11.26 -> 11.26No clear effect
replace xr-egopose with proposed modelxr-egopose · Synthetic data (60 test sequences)3D keypoint error (cm): 13.26 -> 11.76Improved
add synthetic data to real training dataOurs I (real only) · Real video test3D keypoint error: 15.70 -> 14.87Improved
add synthetic data to real training dataxr-egopose I · Real video test3D keypoint error: 16.86 -> 17.29Hurt

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