AI Paper Atlas

Research map / 3D vision / Human pose estimation

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

Can Wang, Jiefeng Li, Wentao Liu, Chen Qian, Cewu Lu

ECCV 2020 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 74 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 HMOR supervision (joint, part, instance relations) over vanilla baseline (ablation)HMOR integrated model · 3DPWMPJPE: 95.7 -> 88.3Improved
add HMOR supervision over baseline (ablation)HMOR integrated model · 3DPWABS-MPJPE: 169.3 -> 119.6Improved
add absolute-pose L1 loss to baseline (ablation)HMOR integrated model · 3DPWABS-MPJPE: 169.3 -> 158.2Improved
use HMOR instead of L_abs supervision (ablation)HMOR integrated model · 3DPWABS-MPJPE: 158.2 -> 119.6Improved
add instance relation (on top of joint+part) (ablation)HMOR integrated model · 3DPWABS-MPJPE: 125.9 -> 119.6Improved
add part relation to joint+instance (ablation)HMOR integrated model · 3DPWPA-MPJPE: 58.5 -> 57.8Improved
add joint relation to part+instance (ablation)HMOR integrated model · 3DPWMPJPE: 89.5 -> 88.3Improved
use vector part relations instead of particle representation (ablation)HMOR integrated model · 3DPWMPJPE: 89.0 -> 88.3Improved
add random virtual view sampling during training (ablation)HMOR integrated model · 3DPWMPJPE: 88.3 -> 87.7Improved
add coarse-to-fine depth refinement (ablation)HMOR integrated model · 3DPWABS-MPJPE: 133.6 -> 118.5Improved
compare with Moon et al. on MuPoTS-3D absolute poseHMOR integrated model · MuPoTS-3D3DPCK_abs: 31.5 -> 43.8Improved
compare with Zanfir on CMU PanopticHMOR integrated model · CMU PanopticMPJPE: 72.1 -> 51.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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