# PGGT-Loc: Feed-Forward Camera Localization with Primitive-Grounded Geometry Transformer

- Source: arXiv cs.RO
- Published: 2026-11-02T05:00:00.000Z
- RoboHot: https://robohot.news/en/items/k064pulzc2k9bn4o3va2eirrg
- Original: https://arxiv.org/abs/2610.41833

## Summary

The authors propose PGGT (Primitive-Grounded Geometry Transformer), a network that takes a single query image and a set of planar map primitives as input and directly predicts a 6-DoF camera pose, enabling feed-forward camera localization. The method sets new state-of-the-art localization performance on both dense surface maps and minimal layout models. Code and models are publicly available, and the paper was accepted to NeurIPS 2026.