GALoc: Gravity Aligned Wireframes for Depth-Free Monocular Floorplan Localization

GALoc is a geometry-first approach for indoor localization that replaces depth prediction with gravity-aligned wireframes, ensuring verticality and coplanarity by construction. Using monocular RGB, camera intrinsics, relative poses, and IMU orientation, it builds a linear constraint matrix and finds the camera gauge that minimizes its smallest singular value through a global search. The resulting wireframes are projected into bird’s-eye-view layouts and matched against floorplans via a metric-free SE(2) search, achieving up to 88% sequential localization success on Gibson datasets and outperforming depth-based baselines when sufficient wall geometry is visible.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.