AI Paper Atlas

Research map / 3D vision / Human pose estimation

StablePose: Learning 6D Object Poses From Geometrically Stable Patches

Yifei Shi, Junwen Huang, Xin Xu, Yifan Zhang, Kai Xu

CVPR 2021 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 47 citations (OpenAlex)

Check 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 geometrically stable patch triplets rather than one-patch groups (ablation)StablePose · T-LESS SISOe_ADI recall: 0.70 -> 0.88Improved
Use geometrically stable patch triplets rather than two-patch groups (ablation)StablePose · T-LESS SISOe_ADI recall: 0.76 -> 0.88Improved
Use geometrically stable patch triplets rather than five-patch groups (ablation)StablePose · T-LESS SISOe_ADI recall: 0.73 -> 0.88Improved
Use stability-based rather than size-based patch-group sampling (ablation)StablePose · T-LESS SISOe_ADI recall: 0.85 -> 0.88Improved
Use stability-based rather than distance-based patch-group sampling (ablation)StablePose · T-LESS SISOe_ADI recall: 0.77 -> 0.88Improved
Add patch-wise pose estimation (ablation)StablePose · T-LESS SISOe_ADI recall: 0.73 -> 0.88Improved
Use back-propagate-with-all rather than baseline symmetry handling (ablation)StablePose · T-LESS SISOe_VSD recall: 0.54 -> 0.73Improved
Use StablePose instead of the strongest listed baseline6D pose estimation · T-LESSe_ADI/e_VSD recall: 0.86 vs 0.76 (VIVO e_ADI); 0.88 vs 0.75 (SISO e_ADI); 0.69 vs 0.50 (VIVO e_VSD); 0.73 vs 0.64 (SISO e_VSD)Improved
Use StablePose instead of CASScategory-level pose estimation · ShapeNetPose10°10cm: 13.9 -> 21.4Improved
Use depth-only StablePose instead of RGBD CosyPose6D pose estimation · LineMOD-O SISOe_ADI/ADD recall: 0.68 -> 0.63Hurt

Later papers that compared with this method

2 later accepted papers report StablePose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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