AI Paper Atlas

Research map / 3D vision / Human pose estimation

PARE: Part Attention Regressor for 3D Human Body Estimation

Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, Michael J. Black

ICCV 2021 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 458 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
supervise attention branch with part segmentation instead of none (ablation)PARE · 3DPW-OCCPA-MPJPE: 62.7 -> 61.2Improved
use part supervision then drop it (mixed) instead of part supervision throughout (ablation)PARE · 3DPWMPJPE: 94.5 -> 93.4Improved
use mixed supervision instead of part supervision throughout (ablation)PARE · 3DPW-OCCPA-MPJPE: 61.2 -> 61.6No clear effect
soft attention instead of pooling with part supervision (ablation)PARE · 3DPW-OCCPA-MPJPE: 64.8 -> 61.2Improved
soft attention instead of pooling with joint supervision (ablation)PARE · 3DPW-OCCMPJPE: 95.4 -> 98.9Hurt
part segmentation instead of joint supervision with soft attention (ablation)PARE · 3DPW-OCCPA-MPJPE: 63.9 -> 61.2Improved
add SynthOcc augmentation (ablation)PARE · 3DPWMPJPE: 95.0 -> 94.5Improved
add random crop on top of SynthOcc (ablation)PARE · 3DPW-OCCPA-MPJPE: 61.2 -> 62.6Hurt
use HRNet-W32 instead of ResNet-50 (ablation)PARE · 3DPWPA-MPJPE: 57.1 -> 54.3Improved
replace HMR-EFT with PARE (ResNet-50)HMR-EFT · 3DPWPA-MPJPE: 59.9 -> 57.1Improved
replace HMR-EFT with PARE (HRNet-W32)HMR-EFT · 3DPWPA-MPJPE: 55.9 -> 54.3Improved
replace SPIN with PARESPIN · 3DOHPA-MPJPE: 68.3 -> 44.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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