AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

Heng Zhao, Shenxing Wei, Dahu Shi, Wenming Tan, Zheyang Li, Ye Ren, Xing Wei, Yi Yang, Shiliang Pu

ICCV 2023 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 33 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
use GCPose instead of OVE6D without ICPunseen-object 6D pose estimation · T-LESSAR: 0.523 -> 0.679Improved
use GCPose instead of OVE6D without ICPunseen-object 6D pose estimation · LINEMODAR: 0.701 -> 0.841Improved
use GCPose without ICP versus OVE6D with ICPunseen-object 6D pose estimation · LINEMODAR: 0.835 -> 0.841Improved
add special data augmentation for synthetic depth training (ablation)GCPose · T-LESS (GT label and mask)AR: 0.635 -> 0.669Improved
add point cloud normalization by model diameter (ablation)GCPose · T-LESS (GT label and mask)AR: 0.669 -> 0.698Improved
add global-aware fine-level features (ablation)GCPose · T-LESS (GT label and mask)AR: 0.698 -> 0.708Improved
add symmetry-aware matching loss (ablation)GCPose · T-LESS (GT label and mask)AR: 0.708 -> 0.738Improved
scale training data by adding 100k ABC CAD models to ShapeNet (ablation)GCPose · T-LESSAR: 0.679 -> 0.724Improved
scale training data with ABC on TUD-L (ablation)GCPose · TUD-LAR: 0.926 -> 0.942Improved
use ground-truth label and mask instead of Mask R-CNN segmentationGCPose · T-LESSAR: 0.679 -> 0.738Improved

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