AI Paper Atlas

Research map / 3D vision / Human pose estimation

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models

Xingyi He, Jiaming Sun, Yuang Wang, Di Huang, Hujun Bao, Xiaowei Zhou

NeurIPS 2022 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 29 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 keypoint-free semi-dense reconstruction and direct sparse-to-dense 2D-3D matchingOnePose++ · OnePose-LowTexture3cm-3deg pose success rate: 35.7 -> 57.7Improved
use keypoint-free semi-dense reconstruction and direct sparse-to-dense 2D-3D matchingOnePose++ · LINEMODADD(S)-0.1d: 63.6 -> 76.9Improved
use keypoint-free semi-dense reconstruction and direct sparse-to-dense 2D-3D matchingOnePose++ · OnePose-LowTexture (objects with scanned models)ADD(S)-0.1d: 62.7 -> 88.9Improved
include point-cloud refinement rather than using coarse reconstruction only (ablation)OnePose++ · OnePose1cm-1deg pose success rate: 43.9 -> 51.1Improved
include point-cloud refinement rather than using coarse reconstruction only (ablation)OnePose++ · OnePose-LowTexture point cloud1mm accuracy: 26.6 -> 30.9Improved
include the 2D-3D attention module instead of directly matching backbone features (ablation)OnePose++ · OnePose-LowTexture5cm-5deg pose success rate: 55.3 -> 72.1Improved
use keypoint-free reconstruction and matching instead of OnePose's keypoint-based approachOnePose++ · OnePose1cm-1deg pose success rate: 49.7 -> 51.1No clear effect
use keypoint-free reconstruction and matching instead of OnePose's keypoint-based approachOnePose++ · LINEMODProj2D: 78.1 -> 94.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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