OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications
This work solves the problem of scalable and private 6DoF localization for AR applications, particularly in indoor spaces, by proposing a federated approach, which is incremental as it builds on existing VPS methods but introduces a novel distributed framework.
The paper tackles the problem of enabling large-scale augmented reality applications by addressing the limitations of centralized Visual Positioning Systems (VPS) that fail to cover private indoor spaces due to privacy and maintenance issues, and presents OpenFLAME, a federated VPS backend that allows independent organizations to manage their own VPS services, resulting in improved coverage and access control without sharing private data.
World-scale augmented reality (AR) applications need a ubiquitous 6DoF localization backend to anchor content to the real world consistently across devices. Large organizations such as Google and Niantic are 3D scanning outdoor public spaces in order to build their own Visual Positioning Systems (VPS). These centralized VPS solutions fail to meet the needs of many future AR applications -- they do not cover private indoor spaces because of privacy concerns, regulations, and the labor bottleneck of updating and maintaining 3D scans. In this paper, we present OpenFLAME, a federated VPS backend that allows independent organizations to 3D scan and maintain a separate VPS service for their own spaces. This enables access control of indoor 3D scans, distributed maintenance of the VPS backend, and encourages larger coverage. Sharding of VPS services introduces several unique challenges -- coherency of localization results across spaces, quality control of VPS services, selection of the right VPS service for a location, and many others. We introduce the concept of federated image-based localization and provide reference solutions for managing and merging data across maps without sharing private data.