AI Paper Atlas

Research map / 3D vision / Human pose estimation

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild

Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Vincent Leroy, Grégory Rogez

ECCV 2020 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 51 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 expert pseudo ground truth for missing parts (DOPE without distillation loss vs gt-only) (ablation)whole-body network · RenderedHand testAUC: 81.1 -> 83.5Improved
add expert pseudo ground truth for missing parts (ablation)whole-body network · Menpo 3D tracking testAUC: 61.7 -> 75.2Improved
add expert pseudo ground truth for missing parts (ablation)whole-body network · MPII (1000 held-out train images)PCKh@0.5: 88.3 -> 88.3No clear effect
add expert pseudo ground truth for missing parts (ablation)whole-body network · MuPoTs-3DPCK3D: 66.6 -> 66.4No clear effect
add distillation loss (ablation)whole-body network · RenderedHand testAUC: 83.5 -> 84.9Improved
add distillation loss (ablation)whole-body network · MPII (1000 held-out train images)PCKh@0.5: 88.3 -> 88.8Improved
add distillation loss (ablation)whole-body network · MuPoTs-3DPCK3D: 66.4 -> 67.2Improved
add distillation loss (ablation)whole-body network · Menpo 3D tracking testAUC: 75.2 -> 75.0No clear effect
reduce image size to 400px, 50 proposals, half precisionDOPE · Inference speed (NVIDIA T4)runtime per image (ms): 100 -> 28Mixed
train on union of partial datasets (unannotated parts treated as negatives) (ablation)whole-body network · hand and face detectionperformance drop: ~10% drop for hands and faces, ~2% for bodiesHurt

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