AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Pose Machines with Self-supervised Learning

Keze Wang, Liang Lin, Chenhan Jiang, Chen Qian, Pengxu Wei

TPAMI 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 105 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 self-supervised correction in training (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 80.15 -> 67.63Improved
add self-supervised correction at test time (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 67.63 -> 63.67Improved
add 3D-to-2D projection instead of direct 2D and 3D multi-task regression (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 86.80 -> 63.67Improved
add temporal LSTM dependency in training (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 90.83 -> 63.67Improved
use sequence input at test time (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 67.70 -> 63.67Improved
add external 2D pose data from MPII (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 111.3 -> 63.67Improved
use 2D ground truth for correction (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 63.67 -> 59.41Improved
use hourglass features for 2D pose network (ablation)3D pose machine · Human3.6M Protocol #13D pose error (mm): 63.67 -> 62.85Improved
replace multi-stage refinement with 3D-to-2D projector (vs conference version)3D pose machine · Human3.6M Protocol #13D pose error (mm): 73.10 -> 63.67Improved
compare to best prior method under per-action training3D pose machine · Human3.6M Protocol #1 (per action)3D pose error (mm): 69.73 -> 63.79Improved
compare to best prior method3D pose machine · Human3.6M Protocol #23D pose error (mm): 79.6 -> 63.74Improved
compare to best prior method3D pose machine · Human3.6M Protocol #33D pose error (mm): 70.70 -> 54.14Improved

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