AI Paper Atlas

Research map / 3D vision / Human pose estimation

RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation

Junwen Huang, Shishir Reddy Vutukur, Peter KT Yu, Nassir Navab, Slobodan Ilic, Benjamin Busam

ICCV 2025 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 3 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 fine predictor with narrowed template sampling (ablation)RayPose coarse · LM-O (ablation)AR: 39.6 -> 42.1Improved
add external MegaPose refinement to fine predictor (ablation)RayPose Fine · LM-O (ablation)AR: 42.1 -> 56.2Improved
predict relative pose to templates instead of absolute pose (ablation)RayPose · LM-O (ablation)AR: 35.4 -> 39.6Improved
use multiple posed templates instead of single view (ablation)RayPose · LM-O (ablation)AR: 32.5 -> 35.4Improved
input ground-truth template pose maps (ablation)RayPose · LM-O (ablation)AR: 27.8 -> 39.6Improved
random template sampling instead of fixed templates for coarse predictor (ablation)RayPose Coarse · LM-O (template distribution)AR: 60.28 -> 65.58Improved
narrow template range to +-30deg, +-5cm (ablation)RayPose Fine · LM-O (template distribution)AR: 65.81 -> 67.29Improved
over-narrow template range to +-15deg, +-3cm (ablation)RayPose Fine · LM-O (template distribution)AR: 67.29 -> 61.04Hurt
wide range +-90deg, +-10cm versus random coarse sampling (ablation)RayPose Fine · LM-O (template distribution)AR: 65.58 -> 65.81No clear effect
replace FoundPose with RayPose, no refinementFoundPose · BOP 5-dataset averageAR: 37.8 -> 39.1Improved
replace FoundPose with RayPose on IC-BIN, no refinementFoundPose · BOP IC-BINAR: 23.9 -> 21.8Hurt
replace GigaPose with RayPose on IC-BIN, with refinementGigaPose · BOP IC-BINAR: 44.3 -> 41.6Hurt

Later papers that compared with this method

1 later accepted paper reports RayPose 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 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