atlas

Research map / 3D vision / Human pose estimation

Segmentation-Driven 6D Object Pose Estimation

CVPR 2019 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 336 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
combine local keypoint predictions using confidence-guided fusion instead of using the center-grid prediction alone (ablation)Segmentation-driven pose estimation · Occluded-LINEMODREP-5px: 39.1 -> 44.9Helped
select the single highest-confidence prediction per keypoint rather than using no fusion (ablation)Segmentation-driven pose estimation · Occluded-LINEMODREP-5px: 39.1 -> 44.0Helped
use the 10 most confident predictions per keypoint for RANSAC rather than the 2 most confident (ablation)Segmentation-driven pose estimation · Occluded-LINEMODREP-5px: 44.5 -> 44.9Helped
use local segmentation-guided pose predictions rather than global pose inference6D object pose estimation · YCB-VideoADD-0.1d: 33.6 -> 39.0Helped
use local segmentation-guided pose predictions rather than global pose inference6D object pose estimation · YCB-VideoREP-5px: 23.1 -> 30.8Helped
use local segmentation-guided pose predictions rather than the strongest listed baseline6D object pose estimation · Occluded-LINEMODREP-5px: 43.1 -> 44.9Helped

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