MVP-SLAM: Multi-Camera Visual-Inertial Floorplan-Prior SLAM

2026-09-30

AI Summary

This study addresses the problem of SLAM trajectory drift in indoor construction sites caused by drastic illumination changes and repetitive textures. To mitigate this, we propose an online correction method leveraging dual fisheye cameras and inertial data. A key contribution is a novel drift-awareness strategy that operates without depth sensors, relying solely on visual inputs and floor plan priors. Specifically, the system performs online matching between observed walls and architectural floor plans, integrating multi-camera fusion with incremental optimization to achieve real-time localization correction. The proposed approach demonstrated strong effectiveness and robustness by securing second place (RMSE 0.29 m) in the localization track and fifth place (0.24 m) in the SLAM track of the Hilti-Trimble Challenge.

Abstract

Indoor building construction sites are demanding environments for visual SLAM, where variable lighting and repetitive, low-textured structures make the system drift over long trajectories, though structural elements such as walls remain distinguishable despite these conditions. These buildings are constructed according to their as-planned floor plans, available from the design phase, and although the actual as-built site can differ from this design, floor plans still provide a metric reference, both to localize the system in the building and to correct drift. Existing methods often use the floor plan to correct an already-built trajectory offline, and those that instead correct it online typically rely on depth sensors. We instead present MVP-SLAM, an online visual-inertial SLAM on two opposite-facing fisheye cameras that corrects drift from cameras alone by matching walls detected in its map to the floor plan, through a drift-aware policy. A multi-stage integration then turns each matched pair incrementally into a persistent correction, so the trajectory stays corrected and localized within the floor plan as it is built. MVP-SLAM was validated on the multi-floor construction sites of the Hilti-Trimble SLAM Challenge 2026, ranking 2nd of 22 teams in the Localization task (0.29 m mean RMSE) and 5th of 62 teams in the SLAM task (0.24 m), the top-ranked one in both tasks among those that operate online, integrate the floor plan, and localize within it.

Problem

• Visual SLAM
• Indoor construction sites
• Drift correction
• Floorplan prior
• Online localization

Innovation

• Multi-Camera Visual-Inertial SLAM
• Floorplan Prior
• Drift Correction
• Fisheye Cameras
• Wall Matching