AI Paper Atlas

Research map / 3D vision / Human pose estimation

GANerated Hands for Real-Time 3D Hand Tracking From Monocular RGB

CVPR 2018 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 555 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
replace synthetic-only training images with GANerated images (ablation)RegNet · Stereo dataset (12 sequences)3D PCK@50mm: ≈0.55 -> ≈0.80Helped
add color augmentation to synthetic training images (ablation)RegNet · Stereo dataset (12 sequences)3D PCK@50mmHelped
add the ProjLayer to link and refine 2D and 3D predictions (ablation)RegNet trained with GANerated images · Stereo dataset3D PCKHelped
use GANerated images instead of synthetic-only training data (ablation)RegNet · Stereo dataset3D PCKHelped
use the proposed method rather than Zimmermann and Broxmonocular RGB hand pose estimation · Dexter+Object2D PCKHelped
use the proposed method rather than Zimmermann and Broxmonocular RGB hand pose estimation · EgoDexter2D PCKHelped
use the proposed method rather than existing methodsmonocular RGB hand pose estimation · Stereo dataset3D PCKHelped
use RGB-only input rather than RGB-D inputthe proposed hand tracker · Dexter+Objectmean error: ≈5cm vs. ≈2cmHurt

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