cs.CVOct 30, 2026

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

Authors: Hanqiao Ye, Yuzhou Liu, Mengqi Rong, Jian Liu, Yangdong Liu, Shuhan Shen

Organizations: School of Artificial Intelligence, University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · 3Beihang University

Abstract

Camera localization methods are mostly multi-stage pipelines relying on dedicated and complex maps that are costly to construct, store, and maintain over time. Alternatively, well-structured maps that organize scenes with compact yet expressive primitives are often readily available, providing rich structural and semantic cues that humans can interpret. However, their potential for direct camera localization remains largely unexplored due to the significant modality gap between map primitives and visual observations. This motivates a new concept for localization, which estimates camera poses by grounding query observations to map primitives. In this paper, we instantiate the concept in the context of planar primitives with PGGT, the Primitive-Grounded Geometry Transformer network. Given a single query image and a set of planar map primitives, the network is trained to predict multiple localization targets for feed-forward 6-DoF camera localization that generalizes to unseen environments. With this straightforward and scalable architecture, our method pushes the state-of-the-art localization performance on both dense surface maps and minimal layout models. The code and models are available at https://github.com/3dv-casia/PGGT-Loc

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives

    Jun 3, 2026Ayumi Umemura, Toshinori Kuwahara, Marc Pollefeys +1Floor-Plan-Based Visual LocalizationCamera Pose Estimation

  2. PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matching

    Mar 21, 2026Hanqiao Ye, Yuzhou Liu, Yangdong Liu +1Camera Pose EstimationMap-Based Localization

  3. Deep Prior Learning for Embodied Perception

    Oct 4, 2026Yimou Wu, Jiaxin Guo, Yun-hui Liu +13D ViTsCamera Pose Estimation