Lazy Visual Localization via Motion Averaging

TL;DR

LazyLoc introduces a scene-reconstruction-free visual localization method using motion averaging, achieving high accuracy and versatility in complex scenarios, with reduced pre-processing and storage needs.

Contribution

It presents a novel approach to visual localization that bypasses scene reconstruction, enabling efficient and accurate pose estimation in various configurations.

Findings

Achieves comparable accuracy to structure-based methods.

Reduces database pre-processing time and storage requirements.

Extends easily to multi-query and camera rig scenarios.

Abstract

Visual (re)localization is critical for various applications in computer vision and robotics. Its goal is to estimate the 6 degrees of freedom (DoF) camera pose for each query image, based on a set of posed database images. Currently, all leading solutions are structure-based that either explicitly construct 3D metric maps from the database with structure-from-motion, or implicitly encode the 3D information with scene coordinate regression models. On the contrary, visual localization without reconstructing the scene in 3D offers clear benefits. It makes deployment more convenient by reducing database pre-processing time, releasing storage requirements, and remaining unaffected by imperfect reconstruction, etc. In this technical report, we demonstrate that it is possible to achieve high localization accuracy without reconstructing the scene from the database. The key to achieving this owes to a tailored motion averaging over database-query pairs. Experiments show that our visual localization proposal, LazyLoc, achieves comparable performance against state-of-the-art structure-based methods. Furthermore, we showcase the versatility of LazyLoc, which can be easily extended to handle complex configurations such as multi-query co-localization and camera rigs.