Multi-Resolution Voxelized Map-Based Stereo Visual-Inertial Odometry

2026-07-19

AI Summary

This work addresses the challenge of real-time local map loading on edge devices, where large-scale prior map data and limited bandwidth hinder efficient operation. To overcome this, the authors propose a multi-resolution voxelized representation of the prior map, wherein each voxel retains only a single representative map point. They further introduce a conical indexing scheme integrated with the 3D Digital Differential Analyzer (DDA) algorithm to enable efficient feature matching and pose estimation. This approach substantially reduces both data transmission requirements and online computational overhead. Experimental validation on two public datasets demonstrates that the method maintains high-precision localization performance even under extremely low-bandwidth conditions.

Abstract

Incorporating prior maps significantly enhances the accuracy and robustness of pose estimation in visual-inertial odometry (VIO). However, the large data volume of such maps, combined with limited transmission bandwidth, makes it impractical to continuously load local maps onto an edge device. In this paper, we propose a multi-resolution prior map construction method and a corresponding map-based VIO system. The prior map is voxelized at multiple resolutions, with each voxel retaining only a single map point. During online VIO operation, a cone-shaped indexing strategy associates 2D features on the edge device with 3D map points. The cone's intercept is determined by the distance from the current position to the 3D points, enabling the selection of the appropriate resolution level and the retrieval of the unique map point within the corresponding voxel via a 3D digital differential analyzer (DDA) algorithm. This approach minimizes both the volume of data required for transmission and the computational load during data association. Extensive experiments on two public datasets demonstrate that our system achieves accurate pose estimation while requiring minimal data transmission.

Problem

• visual-inertial odometry
• prior map
• data transmission
• edge device
• map-based localization

Innovation

• multi-resolution voxelization
• visual-inertial odometry
• prior map
• cone-shaped indexing
• 3D DDA algorithm