AI Paper Atlas

Research map / 3D vision / Human pose estimation

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

Yang You, Ruoxi Shi, Weiming Wang, Cewu Lu

CVPR 2022 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 42 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 CPPF with synthetic-object training instead of the Gao et al. sim-to-real baselineNOCS REAL275 · NOCS REAL275 testmAP (10° 5 cm): 17.1 -> 44.9Improved
Use CPPF instead of Gao et al.SUN RGB-D chair evaluation · SUN RGB-D chairs, validationmAP (60° 30 cm): 7.0 -> 17.6Improved
Use a bounding-box mask instead of an instance maskCPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 35.3Hurt
Use 2° orientation bins instead of 1.5° (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 46.6Improved
Use 1° orientation bins instead of 1.5° (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 38.2Hurt
Use 4° orientation bins instead of 1.5° (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 42.7Hurt
Use 10,000 point pairs instead of 100,000 (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 27.2Hurt
Use 60,000 point pairs instead of 100,000 (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 42.8Hurt
Use 200,000 point pairs instead of 100,000 (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 44.9 -> 45.5Improved
Add auxiliary orientation classification (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 31.7 -> 44.9Improved
Add coarse-to-fine voting to filter noisy points (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 27.4 -> 44.9Improved
Use classification instead of direct regression for voting statistics (ablation)CPPF · NOCS REAL275 testmAP (10° 5 cm): 12.7 -> 44.9Improved

Later papers that compared with this method

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

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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