AI Paper Atlas

Research map / 3D vision / Human pose estimation

MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation

Xinhang Liu, Jiawei Shi, Zheng Dang, Yuchao Dai

ICCV 2025 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 1 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 Self-Attention between Points (SAP) (ablation)MixRI · BOP YCB-V/LM-O/TUD-L mean (attention ablation)mean AR: 2.6 -> 11.9Improved
add Mix-Attention between Reference & Query (MARQ) (ablation)MixRI · BOP YCB-V/LM-O/TUD-L mean (attention ablation)mean AR: 2.6 -> 22.8Improved
add both SAP and MARQ (ablation)MixRI · BOP YCB-V/LM-O/TUD-L mean (attention ablation)mean AR: 2.6 -> 39.5Improved
add MARQ on top of SAP (ablation)MixRI · BOP YCB-V/LM-O/TUD-L mean (attention ablation)mean AR: 11.9 -> 39.5Improved
enable occlusion flags with tau_occ 0.8 (ablation)MixRI · BOP 7 core datasets (no refinement), occlusion thresholdmean AR: 30.7 -> 34.1Improved
use tau_occ 0.8 instead of 0.5 (ablation)MixRI · BOP 7 core datasets (no refinement), occlusion thresholdmean AR: 31.8 -> 34.1Improved
increase reference images from 12 to 24 at test timeMixRI · BOP 7 core datasets (no refinement)mean AR: 31.4 -> 34.1Improved
increase test-time reference images beyond 60 (ablation)MixRI · BOP YCB-V/LM-O/TUD-LARHurt
increase number of correspondences up to about 2400 (ablation)MixRI · BOP YCB-V/LM-O/TUD-LARImproved
use MixRI instead of GigaPose with 4 reference imagesGigaPose · BOP YCB-V/LM-O/TUD-L meanmean AR: 9.1 -> 17.9Improved
use MixRI instead of GigaPose with 24 reference imagesGigaPose · BOP YCB-V/LM-O/TUD-L meanmean AR: 18.3 -> 39.5Improved
add MegaPose refinement to MixRI (12 ref)MixRI · BOP 7 core datasets (no refinement)mean AR: 31.4 -> 45.6Improved

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