AI Paper Atlas

Research map / 3D vision / Human pose estimation

OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation

Yuchen Che, Ryo Furukawa, Asako Kanezaki

ECCV 2024 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 4 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
use object-level alignment before part segmentation, instead of EAP's part-by-part iterative schemeOP-Align · Synthetic datasetSegmentation IoU: 68.46 -> 80.70Improved
replace EAP with OP-Align (no iterative operations)self-supervised articulated pose estimation · Synthetic datasetInference speed (FPS): <1 -> 41Improved
replace EAP with OP-Alignself-supervised articulated pose estimation · Synthetic datasetGPU memory (GB): 9.23 -> 2.31Improved
replace EAP with OP-Alignself-supervised articulated pose estimation · Synthetic datasetJoint direction error (degree): 23.09 -> 6.63Improved
replace EAP with OP-Alignself-supervised articulated pose estimation · Synthetic datasetTranslation error: 0.121 -> 0.129Hurt
add shape variance regularization L_regS (ablation)OP-Align · Real-world dataset (laptop)Joint and part mAPImproved
add density regularization L_regD (ablation)OP-Align · Real-world datasetoverall mAPImproved
add segmentation regularization L_regW (ablation)OP-Align · Real-world datasetjoint parameter validityImproved
add joint pivot regularization L_regJ (ablation)OP-Align · Real-world datasetjoint and part pose mAPImproved
self-supervised OP-Align vs supervised PointNet++OP-Align · Real-world datasetSegmentation mAP IoU50%: 42.20 -> 50.42Improved
apply OP-Align to basket category with small movable handlesOP-Align · Real-world basketqualitative segmentationHurt

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