Gravity aligned wireframes improve indoor floorplan localization accuracy
GALoc: Gravity Aligned Wireframes for Depth-Free Monocular Floorplan Localization
Computer Vision and Pattern RecognitionRobotics
Summary
Indoor localization often uses floorplans, but previous methods depend on depth predictions that struggle in cluttered spaces. The authors propose GALoc, a method that uses geometry and gravity orientation to create simplified building shapes without needing depth data. GALoc aligns these shapes to match floorplans by ensuring walls are vertical and flat together, improving accuracy. Tests show GALoc works better than depth-based methods when enough wall detail is visible and smartly avoids uncertain scenes.
What this means in practice
- •For indoor navigation system developers: Enable accurate camera localization inside buildings using only RGB cameras and IMU data without relying on depth sensors.$Commercial implications: Makes practical, cost-effective indoor localization products possible by removing the need for expensive or unreliable depth sensors.
- •For augmented reality app developers: Improve spatial alignment of AR content indoors by using gravity-aligned geometric constraints to localize the camera relative to known floorplans.
Authors
Jeahn Han, Minji Kim, Jeongbin Sohn, Jonghyeok Park, Matthias Wuest, Pyojin Kim
Abstract
Floorplans are compact, appearance-invariant maps ideal for indoor localization, yet existing methods rely on depth networks that are brittle in cluttered scenes. We propose GALoc, a geometry-first framework that replaces depth prediction with gravity-aligned wireframes that satisfy verticality and coplanarity by construction. Given monocular RGB, camera intrinsics, relative poses, and IMU orientation, GALoc constructs a linear constraint matrix encoding verticality and coplanarity, and finds the camera gauge minimizing its smallest singular value via global search. The rectified wireframes are projected into bird's-eye-view layouts through a closed-form, FOV-consistent transformation and matched against the floorplan via metric-free SE(2) search. We evaluate end-to-end on Structured3D, with calibrated noise on Gibson, and on real-world author-collected sequences. When sufficient wall geometry is visible, GALoc matches or outperforms depth-based baselines -- achieving 88% sequential localization success at 0.1m over 100-step sequences on Gibson vs the baseline's 68% -- while abstaining in structure-blind scenes.