AI Paper Atlas

Research map / 3D vision / Human pose estimation

Unsupervised Pose-Aware Part Decomposition for Man-Made Articulated Objects

Yuki Kawana, Yusuke Mukuta, Tatsuya Harada

ECCV 2022 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 8 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 category-common shape decoder (ablation)PPD · Articulated objects ablation, mean over 5 categorieslabel IoU: 55.67 -> 80.99Improved
add category-common shape decoder (ablation)PPD · Articulated objects ablation, mean over 5 categoriesEPE: 8.827 -> 2.988Improved
add category-common pose decoder (ablation)PPD · Articulated objects ablation, mean over 5 categorieslabel IoU: 71.35 -> 80.99Improved
add category-common pose decoder (ablation)PPD · Articulated objects ablation, mean over 5 categoriesEPE: 7.219 -> 2.988Improved
add variance loss L_var (ablation)PPD · Articulated objects ablation, mean over 5 categorieslabel IoU: 65.29 -> 80.99Improved
add volume loss L_vol (ablation)PPD · Articulated objects ablation, mean over 5 categorieslabel IoU: 72.20 -> 80.99Improved
add deviation loss L_dev (ablation)PPD · Articulated objects ablation, mean over 5 categoriesEPE: 6.628 -> 2.988Improved
add location loss L_loc (ablation)PPD · Articulated objects ablation, mean over 5 categoriesEPE: 9.250 -> 2.988Improved
add adversarial loss (ablation)PPD · Articulated objects ablation, mean over 5 categorieslabel IoU: 70.14 -> 80.99Improved
PPD instead of BSP-Net for part segmentationBSP-Net · Articulated objects, part segmentation (canonical-pose labeling), meanlabel IoU: 76.65 -> 80.99Improved
PPD instead of BAE-Net for part segmentationBAE-Net · Articulated objects, part segmentation (canonical-pose labeling), meanlabel IoU: 39.17 -> 80.99Improved
use depth map input instead of complete point cloudPPD · Depth map vs complete point cloudlabel IoU: 80.99 -> 80.65No clear effect

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