PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matching
For camera relocalization in structured environments, this work provides a lightweight alternative to point-based methods by leveraging planar primitives, though it is incremental as it applies existing matching and pose-solving techniques to a new representation.
This paper introduces PlanaReLoc, a camera relocalization method that uses planar primitives and 3D planar maps instead of point correspondences, achieving effective 6-DoF pose estimation without textured maps, pose priors, or per-scene training, as demonstrated on ScanNet and 12Scenes datasets.
While structure-based relocalizers have long strived for point correspondences when establishing or regressing query-map associations, in this paper, we pioneer the use of planar primitives and 3D planar maps for lightweight 6-DoF camera relocalization in structured environments. Planar primitives, beyond being fundamental entities in projective geometry, also serve as region-based representations that encapsulate both structural and semantic richness. This motivates us to introduce PlanaReLoc, a streamlined plane-centric paradigm where a deep matcher associates planar primitives across the query image and the map within a learned unified embedding space, after which the 6-DoF pose is solved and refined under a robust framework. Through comprehensive experiments on the ScanNet and 12Scenes datasets across hundreds of scenes, our method demonstrates the superiority of planar primitives in facilitating reliable cross-modal structural correspondences and achieving effective camera relocalization without requiring realistically textured/colored maps, pose priors, or per-scene training. The code and data are available at https://github.com/3dv-casia/PlanaReLoc .