AI Paper Atlas

Research map / 3D vision / Human pose estimation

Image-Based Synthesis for Deep 3D Human Pose Estimation

Grégory Rogez, Cordelia Schmid

IJCV 2018 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 246 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 images to real images for training (ablation)pose classifier · Human3.6M P13D pose error (mm): 97.7 -> 88.1Improved
add synthetic images to real images for training (ablation)pose regressor · Human3.6M P13D pose error (mm): 139.6 -> 125.5Improved
train classifier on synthetic instead of real images (190,000 poses) (ablation)pose classifier · Human3.6M P13D pose error (mm): 97.7 -> 97.2No clear effect
use classifier instead of regressor with few training images (17,000) (ablation)pose classifier · Human3.6M P13D pose error (mm): 112.9 -> 149.7Hurt
use classifier instead of regressor with large synthetic+real data (ablation)pose classifier · Human3.6M P13D pose error (mm): 125.5 -> 88.1Improved
train AlexNet from scratch instead of fine-tuning ImageNet model (ablation)pose classifier · Human3.6M P13D pose error (mm): 98.3 -> 88.1Improved
render from in-the-wild 2D images (MPII+LSP) instead of H3.6M images (ablation)pose classifier · LSP2D pose error (pixels): 31.1 -> 20.7Improved
render from in-the-wild 2D images (MPII+LSP) instead of H3.6M images (ablation)pose classifier · Human3.6M2D pose error (pixels): 8.8 -> 17.3Hurt
use CMU 3D poses instead of H3.6M poses (190,000) (ablation)pose classifier · LSP2D pose error (pixels): 20.7 -> 22.4Hurt
increase CMU poses and synthetic images from 190,000 to 2 million (ablation)pose classifier · LSP2D pose error (pixels): 22.4 -> 13.8Improved
increase CMU poses and synthetic images from 190,000 to 2 million (ablation)pose classifier · Human3.6M3D pose error (mm): 150.6 -> 138.0Improved
fine-tune VGG-16 instead of AlexNet (ablation)pose classifier · LSP2D pose error (pixels): 13.8 -> 11.5Improved

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