Re-localization acceleration with Medoid Silhouette Clustering

TL;DR

This paper introduces a novel tree-like search strategy using Medoid Silhouette Clustering to significantly accelerate visual re-localization without compromising accuracy, validated across multiple datasets.

Contribution

The paper proposes a new clustering-based approach for faster visual re-localization, addressing the speed limitations of current neural network methods.

Findings

Achieves 50-90% time savings in re-localization tasks

Maintains high localization accuracy despite acceleration

Validated on three public datasets

Abstract

Two crucial performance criteria for the deployment of visual localization are speed and accuracy. Current research on visual localization with neural networks is limited to examining methods for enhancing the accuracy of networks across various datasets. How to expedite the re-localization process within deep neural network architectures still needs further investigation. In this paper, we present a novel approach for accelerating visual re-localization in practice. A tree-like search strategy, built on the keyframes extracted by a visual clustering algorithm, is designed for matching acceleration. Our method has been validated on two tasks across three public datasets, allowing for 50 up to 90 percent time saving over the baseline while not reducing location accuracy.