AI Paper Atlas

Research map / 3D vision / Human pose estimation

Synthetic Depth Transfer for Monocular 3D Object Pose Estimation in the Wild

Yueying Kao, Weiming Li, Qiang Wang, Zhouchen Lin, Wooshik Kim, Sunghoon Hong

AAAI 2020 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 2 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 synthetic data to real training (ablation)RGB-Net · PASCAL 3D+ GT boxesAcc pi/6 (%): 81.8 -> 85.7Improved
add RGB-to-Depth Embedding (PD-Net) with real+syn data (ablation)RGB-Net · PASCAL 3D+ GT boxesAcc pi/6 (%): 85.7 -> 88.2Improved
add Synthetic-Real Adaptation (SDA) with real+syn data (ablation)RGB-Net · PASCAL 3D+ GT boxesAcc pi/6 (%): 85.7 -> 87.2Improved
add both PD-Net and SDA (ablation)RGB-Net · PASCAL 3D+ GT boxesAcc pi/6 (%): 85.7 -> 89.4Improved
fuse RGB and depth features from synthetic data only (ablation)RGB-Net (Syn) · PASCAL 3D+ GT boxesAcc pi/6 (%): 43.9 -> 76.1Improved
add depth fusion to synthetic-only training vs PD-Net alone (ablation)PD-Net (Syn) · PASCAL 3D+ GT boxesAcc pi/6 (%): 48.8 -> 76.1Improved
add unsupervised domain adaptation (UDA) to synthetic-only RGB-Net with unlabeled real data (ablation)RGB-Net (Syn) · PASCAL 3D+ GT boxesAcc pi/6 (%): 43.9 -> 79.5Improved
add UDA to RGB-Net+PD-Net (ablation)RGB-Net+PD-Net (Syn) · PASCAL 3D+ GT boxesAcc pi/6 (%): 76.1 -> 80.8Improved
use SSD512 detector instead of RCNNOurs(final) · PASCAL 3D+ joint detectionAcc pi/6 (%): 53.4 -> 74.1Improved
evaluate on small vs large objectsOurs(final) · PASCAL 3D+ GT boxesAcc pi/6 (%): 92.4 -> 85.3Hurt

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