AI Paper Atlas

Research map / 3D vision / Human pose estimation

WAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose Estimation

Yulin Wang, Jianghao Zhou, Hongli Li, MENGTING HU, Chen LUO

ECCV 2026 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 0 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
train with wide perturbation range ±90° instead of ±20° (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 68.7 -> 81.8Improved
widen training range to ±180° from ±90° (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 81.8 -> 75.2Hurt
use SAM-generated masks instead of GT masks in training (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 76.8 -> 81.8Improved
add mask input (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 80.7 -> 81.8Improved
add rotational symmetry priors (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 80.1 -> 81.8Improved
add angle-balanced loss (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 78.2 -> 81.8Improved
train on SA6D instead of original GSO PBR data (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 76.1 -> 81.8Improved
attention pooling and transformer encoder instead of average pooling (ablation)WAPR · IC-BIN/TUD-L/LM-O detectionmean AP: 80.3 -> 81.8Improved
increase candidates from 4 to 12 (ablation)WAPR · IC-BIN detectionmean AP: 56.9 -> 70.1Improved
increase candidates from 12 to 60 (ablation)WAPR · IC-BIN detectionmean AP: 70.1 -> 72.1No clear effect
use WAPR as plug-in refiner on FreeZeV2 poses (ablation)FreeZeV2 · IC-BIN/TUD-L/LM-O detectionmean AP: 83.7 -> 84.3Improved
use WAPR as plug-in refiner on GigaPose+GenFlow poses (ablation)GigaPose+GenFlow · IC-BIN/TUD-L/LM-O detectionmean AP: 56.5 -> 57.8Improved

Earlier methods this paper compares with

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