AI Paper Atlas

Research map / 3D vision / Human pose estimation

ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation

Huan Ren, Yihan Chen, Chuxin Wang, Nailong Liu, Wenfei Yang, Tianzhu Zhang

CVPR 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
replace complete-shape recovery with partial instance reconstruction (ablation)ComPose · REAL275 depth-only5deg2cm: 55.6 -> 49.6Hurt
add completed dense point cloud to enhance keypoints (ablation)ComPose · REAL275 depth-only10deg5cm: 83.3 -> 85.0Improved
use progressive completion instead of AdaPoinTr (ablation)ComPose · REAL275 depth-only5deg2cm: 53.4 -> 55.6Improved
use progressive completion instead of PoinTr (ablation)ComPose · REAL275 depth-only5deg2cm: 52.7 -> 55.6Improved
use progressive completion instead of static query (ablation)ComPose · REAL275 depth-only5deg2cm: 51.6 -> 55.6Improved
add adaptive keypoint selection (ablation)ComPose · REAL275 depth-only5deg2cm: 53.8 -> 55.6Improved
add geometric relation encoding (ablation)ComPose · REAL275 depth-only5deg2cm: 49.5 -> 53.8Improved
add geometric relation consistency constraint (ablation)ComPose · REAL275 depth-only5deg2cm: 53.8 -> 55.6Improved
use unified completion-pose instead of two-stage completion-then-pose (ablation)ComPose · REAL275 depth-onlyaccuracy and latencyImproved
apply 25% occlusion augmentation at test time (ablation)AG-Pose* · REAL275 depth-only5deg5cm drop: 16.5%Hurt
apply 25% occlusion augmentation at test time (ablation)ComPose · REAL275 depth-only5deg5cm drop: 12.6%Hurt
use ComPose instead of AG-Pose in depth-only settingpose estimator · REAL275 depth-only5deg2cm: 48.8 -> 55.6Improved

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