AI Paper Atlas

Research map / 3D vision / Human pose estimation

PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation

Yihan Chen, Huan Ren, Wenfei Yang, Hang Du, Tianzhu Zhang, Feng Wu

ECCV 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 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
add the category prior branch with joint deformation and alignment (ablation)PriorPose · REAL275mAP 5deg5cm: 64.4 -> 68.2Improved
couple deformation and alignment jointly instead of serial deform-then-align (ablation)PriorPose · REAL275mAP 5deg5cm: 64.5 -> 68.2Improved
use structured mean-shape prior instead of Gaussian prior (ablation)PriorPose · REAL275mAP 5deg5cm: 65.3 -> 68.2Improved
add shape-consistency losses (ablation)PriorPose · REAL275mAP 5deg5cm: 65.5 -> 68.2Improved
add reconstruction loss with deformation head (ablation)PriorPose · REAL275mAP 5deg2cm: 58.1 -> 60.2Improved
add canonical-space consistency to reconstruction loss (ablation)PriorPose · REAL275mAP 5deg5cm: 65.5 -> 65.9Improved
add camera-space consistency to reconstruction loss (ablation)PriorPose · REAL275mAP 10deg2cm: 80.7 -> 79.8Mixed
combine canonical and camera consistency (ablation)PriorPose · REAL275mAP 5deg5cm: 65.5 -> 68.2Improved
use seeded fusion instead of dense self-attention (ablation)PriorPose · REAL275mAP 5deg5cm: 66.5 -> 68.2Improved
add geometry-quality bias (gamma=0.2) (ablation)PriorPose · REAL275mAP 5deg5cm: 66.4 -> 68.2Improved
reduce kNN size from 32 to 16 (ablation)PriorPose · REAL275mAP 10deg5cm: 88.9 -> 86.2Hurt
increase kNN size from 32 to 64 (ablation)PriorPose · REAL275mAP 5deg5cm: 68.2 -> 67.1Hurt

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