AI Paper Atlas

Research map / 3D vision / Human pose estimation

EgoRenderer: Rendering Human Avatars From Egocentric Camera Images

Tao Hu, Kripasindhu Sarkar, Lingjie Liu, Matthias Zwicker, Christian Theobalt

ICCV 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 16 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 the learned implicit texture stack (vs egocentric texture only) (ablation)EgoRenderer · H1 single-videoLPIPS (x10): 1.769 -> 1.623Improved
add egocentric texture (vs implicit multi-view texture only) (ablation)EgoRenderer · H1 single-videoLPIPS (x10): 1.738 -> 1.623Improved
learn the texture stack during training (vs static explicit texture) (ablation)EgoRenderer · H3 single-videoLPIPS (x10): 1.676 -> 1.569Improved
use texture synthesis with implicit texture instead of direct pose-to-image translation (ablation)Only-MV vs Pix2PixHD · H2 single-videoLPIPS (x10): 1.713 -> 1.626Improved
replace per-frame FeatureNet features with a global implicit texture stack (ablation)EgoRenderer vs Fea-Net · H2 single-videoLPIPS (x10): 1.687 -> 1.617Improved
add the implicit texture stack (vs egocentric texture only) (ablation)EgoRenderer · H4 single-videoSSIM (x10): 7.586 -> 7.535Hurt
add the implicit texture stack (vs static explicit texture), L1 distance (ablation)EgoRenderer · single-video H1 and H3L1 distance (x10): 0.950 -> 0.994 (H1); 1.562 -> 1.448 (H3)Mixed
train on multiple camera videos instead of a single videoIm-Tex · H1LPIPS (x10): 1.623 -> 1.174Improved
train on multiple camera videos instead of a single videoIm-Tex · H4LPIPS (x10): 1.571 -> 1.246Improved
train on multiple camera videos instead of a single videoIm-Tex · H1SSIM (x10): 7.529 -> 8.134Improved

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