Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization

TL;DR

This paper introduces a cascaded parallel filtering approach for image-based localization that improves memory efficiency and filtering accuracy by leveraging feature, visibility, and geometry information, with enhanced pose estimation techniques.

Contribution

The work presents a novel cascaded parallel filtering method that divides filtering tasks for better memory efficiency and accuracy, incorporating quality-aware spatial reconfiguration and focal length enhancement.

Findings

Achieves competitive localization accuracy on real-world datasets.

Reduces memory consumption compared to existing methods.

Improves filtering robustness through parallel tasks.

Abstract

Image-based localization (IBL) aims to estimate the 6DOF camera pose for a given query image. The camera pose can be computed from 2D-3D matches between a query image and Structure-from-Motion (SfM) models. Despite recent advances in IBL, it remains difficult to simultaneously resolve the memory consumption and match ambiguity problems of large SfM models. In this work, we propose a cascaded parallel filtering method that leverages the feature, visibility and geometry information to filter wrong matches under binary feature representation. The core idea is that we divide the challenging filtering task into two parallel tasks before deriving an auxiliary camera pose for final filtering. One task focuses on preserving potentially correct matches, while another focuses on obtaining high quality matches to facilitate subsequent more powerful filtering. Moreover, our proposed method improves the localization accuracy by introducing a quality-aware spatial reconfiguration method and a principal focal length enhanced pose estimation method. Experimental results on real-world datasets demonstrate that our method achieves very competitive localization performances in a memory-efficient manner.