← Back to the feed
Space & aviationResearch findings

GAP-GDRNet · Geometry-Aware Monocular 6D Pose Estimation for Spacecraft

Original published 2026.07.03 01:02 KSTAdded to Blackdeck 2026.11.20 22:03 KST

What has changed?

Enhances geometric guidance by integrating local texture enhancement and structured geometric region alignment in pose regression

Key points

  1. Proposes a geometry-aware monocular 6D pose estimation method for spacecraft under weak texture and occlusion
  2. Introduces AFR and PGSA modules to improve local texture handling and geometric consistency in pose prediction
  3. Achieves 1.96° rotation error and 0.0165 m translation error on a synthetic spacecraft benchmark

Connect it to your work

A geometry-aware framework enables accurate 6D pose estimation under weak texture and occlusion conditions

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivGAP-GDRNet: Geometry-aware monocular 6D pose estimation for spacecraft using synthetic geometric supervision