AI Paper Atlas

Research map / 3D vision / Human pose estimation

Optimizing Network Structure for 3D Human Pose Estimation

Hai Ci, Chunyu Wang, Xiaoxuan Ma, Yizhou Wang

ICCV 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 289 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
replace FCN with locally connected network (3-NN)Martinez FCN · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 63.21 -> 57.56Improved
replace GCN shared-weight filters with per-joint weights (LCN) (ablation)Defferrard GCN · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 66.37 -> 57.56Improved
use GCN instead of FCNFCN · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 63.21 -> 66.37Hurt
increase neighbourhood from 1-NN to 2-NN (ablation)LCN · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 58.77 -> 57.73Improved
increase neighbourhood from 3-NN to 4-NN (ablation)LCN · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 57.56 -> 58.37Hurt
learn structure matrix values on top of 2-NN (ablation)LCN (2-NN) · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 57.73 -> 57.80No clear effect
learn the whole structure matrix from data instead of anatomy prior (ablation)LCN · H36M protocol #1 (SH trained on MPII 2D, pixel CS)MPJPE: 57.56 -> 59.22Hurt
remove pose scale using scale-normalised pixel coordinate system instead of camera CS (ablation)Martinez FCN · H36M protocol #1 (SH trained on MPII 2D, pixel vs camera CS)MPJPE: 67.50 -> 63.21Improved
remove pose scale using scale-normalised pixel coordinate system instead of camera CS (ablation)LCN (3-NN) · H36M protocol #1 (SH trained on MPII 2D, pixel vs camera CS)MPJPE: 62.95 -> 57.56Improved
LCN instead of FCN on cross-dataset testMartinez FCN · MPI-INF-3DHP (trained on H36M unless noted) all scenesPCK: 42.5 -> 74.0Improved
LCN instead of FCN when trained on one actionMartinez FCN · H36M cross-action trainingMPJPE: about 20mm smallerImproved
LCN instead of FCN with scarce training dataMartinez FCN · H36M scarce (Direction only)MPJPE: 2k vs 5K examples to saturateImproved

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