OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications

2025-10-04

AI Summary

Centralized visual positioning systems (VPS) suffer from inadequate coverage in privacy-sensitive environments (e.g., private indoor spaces), labor-intensive 3D map updates, and poor adaptability to heterogeneous AR applications. To address these limitations, this paper proposes a federated visual positioning system. Its core is a federated image-based localization framework that integrates federated learning, cross-device image retrieval, incremental 3D scene reconstruction, and map tiling—enabling collaborative localization knowledge sharing and cross-space consistency modeling across organizations without exchanging raw private data. The system achieves seamless indoor-outdoor wide-area coverage, fine-grained access control, and distributed map maintenance. By preserving data privacy, it significantly enhances the scalability, robustness, and service availability of VPS.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Distributed Machine Learning & Federated Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Data transparency and provenance

Abstract

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.

Problem

• Enabling decentralized 6DoF localization for AR across multiple spaces
• Solving privacy and maintenance issues in centralized visual positioning systems
• Managing coherent localization across federated VPS services without data sharing

Innovation

• Federated VPS backend for distributed maintenance
• Enables private indoor 3D scanning with access control
• Manages cross-map localization without sharing private data