AI Paper Atlas

Research map / 3D vision / Human pose estimation

SE(3)-Equivariance with Geometric and Topological Guidance for Category-Level Object Pose Estimation

Sheng Yu, Di-Hua Zhai, Yuanqing Xia

CVPR 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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 topology guidance and SE(3)-equivariance modules to geometry-only baseline (ablation)SEGPose · REAL2755deg5cm: 51.1 -> 61.1Improved
add topology-guided point cloud reconstruction (ablation)SEGPose · REAL2755deg5cm: 58.1 -> 61.1Improved
add SE(3)-equivariance guided pose estimation head (ablation)SEGPose · REAL2755deg5cm: 60.3 -> 61.1Improved
add input data augmentation (ablation)SEGPose · REAL2755deg5cm: 60.7 -> 61.1Improved
add topology module versus SE(3) module alone (ablation)SEGPose · REAL275mAPImproved
add SDF-based bounding box-pose consistency loss Lsdf (ablation)SEGPose · REAL275mAPImproved
use SEGPose instead of HS-Pose (depth-based)category-level pose estimation · Wild6D5deg5cm: 28.6 -> 35.6Improved
use SEGPose instead of HS-Pose in robot graspingUR3 grasping · Single-object graspinggrasp success rate (%): 75.6 -> 88.9Improved
use depth-only SEGPose versus RGB-D SpotPoseREAL275 · REAL2755deg5cm: 64.8 -> 61.1Hurt

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