AI Paper Atlas

Research map / 3D vision / Human pose estimation

Ordinal Depth Supervision for 3D Human Pose Estimation

Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis

CVPR 2018 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 450 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 2D keypoint examples to Human3.6M training (ablation)3D pose ConvNet · Human3.6Mmean per joint error (mm): 71.9 -> 66.6Improved
Add ordinal depth supervision to 2D-keypoint training examples (ablation)3D pose ConvNet · Human3.6Mmean per joint error (mm): 66.6 -> 62.1Improved
Add the reconstruction component (ablation)3D pose ConvNet with 2D keypoint and ordinal supervision · Human3.6Mmean per joint error (mm): 62.1 -> 56.2Improved
Add ordinal depth supervision to in-the-wild 2D-keypoint examples (ablation)3D pose ConvNet trained on Human3.6M · MPI-INF-3DHPPCK3D: 44.3 -> 71.9Improved
Use ordinal supervision rather than 3D-ground-truth direct regression (ablation)Depth prediction ConvNet · Human3.6Mmean per joint error (mm): 80.23 -> 84.24Hurt
Use weak ordinal-depth and 2D-keypoint supervision rather than full 3D supervision (ablation)Coordinate regression ConvNet · Human3.6Mmean per joint error (mm): 112.41 -> 115.08Hurt
Use ordinal supervision rather than full 3D supervision (ablation)Volume regression ConvNet with one hourglass · Human3.6Mmean per joint error (mm): 85.82 -> 89.93Hurt
Use ordinal supervision rather than full 3D supervision (ablation)Volume regression ConvNet with two hourglasses · Human3.6Mmean per joint error (mm): 69.77 -> 79.03Hurt
Add in-the-wild 2D-keypoint and ordinal-depth examples (ablation)3D pose ConvNet trained on Human3.6M · MPI-INF-3DHPAUC: 6.3 -> 19.8 -> 35.3Improved

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