Augmented Reality without Borders: Achieving Precise Localization Without Maps

2024-08-30

arXiv.org

AI Summary

Existing AR localization methods for dynamic, large-scale outdoor scenes rely heavily on pre-built 3D maps, resulting in low pose accuracy and high computational overhead. Method: This paper proposes MARLoc, a map-free visual localization framework that abandons conventional SfM/SLAM paradigms. Instead, it leverages only known relative pose constraints within a single image sequence to perform intra-sequence triangulation, robust 3D–2D correspondence generation, and lightweight iterative pose refinement—enabling end-to-end, real-time, and robust single-sequence localization. Contribution/Results: MARLoc introduces the first geometric localization paradigm that operates entirely within a single sequence without requiring any global 3D map. It achieves state-of-the-art performance on standard benchmarks and real-world outdoor experiments. When deployed on AR devices, it delivers centimeter-level pose accuracy and significantly enhances AR interaction stability in complex, dynamic environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

Visual localization is crucial for Computer Vision and Augmented Reality (AR) applications, where determining the camera or device's position and orientation is essential to accurately interact with the physical environment. Traditional methods rely on detailed 3D maps constructed using Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM), which is computationally expensive and impractical for dynamic or large-scale environments. We introduce MARLoc, a novel localization framework for AR applications that uses known relative transformations within image sequences to perform intra-sequence triangulation, generating 3D-2D correspondences for pose estimation and refinement. MARLoc eliminates the need for pre-built SfM maps, providing accurate and efficient localization suitable for dynamic outdoor environments. Evaluation with benchmark datasets and real-world experiments demonstrates MARLoc's state-of-the-art performance and robustness. By integrating MARLoc into an AR device, we highlight its capability to achieve precise localization in real-world outdoor scenarios, showcasing its practical effectiveness and potential to enhance visual localization in AR applications.

Problem

• Visual Localization
• Augmented Reality
• 3D Mapping

Innovation

• MARLoc
• Visual Localization
• Augmented Reality