AI Paper Atlas

Research map / 3D vision / Human pose estimation

Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference

Chen Zhao, Tong Zhang, Zheng Dang, Mathieu Salzmann

IJCV 2026 · 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 WCV rotation estimation instead of a rotation regression module (ablation)DVMNet++ · CO3Dmean angular error: 31.78 -> 19.95Improved
add voxel weights (2D mask and objectness) to closest voxel algorithm (ablation)DVMNet++ · CO3Dmean angular error: 21.64 -> 19.95Improved
add 2D object mask weights to WCV (ablation)DVMNet++ · CO3Dmean angular error: 21.64 -> 20.92Improved
add voxel objectness weights to WCV (ablation)DVMNet++ · CO3Dmean angular error: 21.64 -> 20.07Improved
add voxel objectness on top of 2D mask (ablation)DVMNet++ · CO3Dmean angular error: 20.92 -> 19.95Improved
add image-retrieval (DINOv2 similarity) proposal selection to detector (ablation)open-set detector · LINEMODtranslation angular error: 5.27 -> 1.55Improved
replace GT bounding box with predicted box from open-set detectorDVMNet++ · CO3Dmean angular error: 19.95 -> 19.64No clear effect
replace GT bounding box with predicted box from open-set detectorDVMNet++ · LINEMODmean angular error: 36.82 -> 39.79Hurt
increase number of reference images from 1 to 7 (ablation)DVMNet++ · CO3Dmean angular error: 19.95 -> 14.93Improved
increase number of reference images from 1 to 7 (ablation)3DAHV · CO3Dmean angular error: 28.44 -> 24.76Improved
increase number of reference images from 1 to 7 (ablation)SuperGlue · CO3Dmean angular error: 71.47 -> 61.74Improved
use hypothesis-free DVMNet++ instead of hypothesis-based 3DAHVpose estimator · CO3Dtime per image pair: 35ms -> 23msImproved

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