Article

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

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.

Part of the event: PGGT: Feed-Forward Camera Localization with Planar Primitive Grounding

This page provides a summary and source link only.