AI Paper Atlas

Research map / 3D vision / Human pose estimation

Explicit Occlusion Reasoning for Multi-Person 3D Human Pose Estimation

Qihao Liu, Yi Zhang, Song Bai, Alan Yuille

ECCV 2022 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 30 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 occluded-keypoint reasoning module to detection (ablation)HUPOR · MuPoTS-3DPCK_rel: 74.87 -> 79.28Improved
add refinement module after reasoning (ablation)HUPOR · MuPoTS-3DPCK_rel: 79.28 -> 86.54Improved
train detection on visible joints only (use occlusion labels) (ablation)HUPOR detection · MuPoTS-3DPCK_rel: 71.12 -> 74.87Improved
train detection on visible joints only (use occlusion labels) (ablation)HUPOR detection · MuPoTS-3DPCK_occ: 56.53 -> 51.48Hurt
use occlusion labels when reasoning module is added (ablation)HUPOR · MuPoTS-3DPCK_rel: 74.76 -> 79.28Improved
replace hourglass reasoning with DSED (ablation)HUPOR · MuPoTS-3DPCK_rel: 75.58 -> 79.28Improved
replace hourglass reasoning with DSED (ablation)HUPOR · MuPoTS-3DPCK_occ: 55.30 -> 61.24Improved
add non-local blocks to DSED (ablation)HUPOR · MuPoTS-3DPCK_rel: 79.28 -> 79.81No clear effect
add DSED reasoning module (ablation)HrHRNet-W48 · COCO val-dev 2017AP: 69.9 -> 70.8Improved
add hourglass reasoning module (ablation)HrHRNet-W48 · COCO val-dev 2017AP: 69.9 -> 68.2Hurt
add hourglass reasoning module (ablation)PifPaf · COCO val-dev 2017AP: 67.4 -> 67.5No clear effect
add DSED reasoning module (ablation)PifPaf · COCO val-dev 2017AP: 67.4 -> 69.1Improved

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