Benchmarking Image Retrieval for Visual Localization

TL;DR

This paper evaluates how different image retrieval methods impact visual localization accuracy, revealing that traditional landmark retrieval metrics do not always correlate with localization performance, thus highlighting the need for specialized retrieval approaches.

Contribution

It introduces a benchmark and evaluation protocols for assessing image retrieval methods specifically for visual localization tasks, emphasizing the gap in current retrieval approaches.

Findings

Retrieval performance on landmark recognition only sometimes correlates with localization accuracy.

Current retrieval algorithms may not be optimal for localization tasks.

A new benchmark setup for localization-specific image retrieval evaluation.

Abstract

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two tasks: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for these tasks. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes. However, robustness to viewpoint changes is not necessarily desirable in the context of visual localization. This paper focuses on understanding the role of image retrieval for multiple visual localization tasks. We introduce a benchmark setup and compare state-of-the-art retrieval representations on multiple datasets. We show that retrieval performance on classical landmark retrieval/recognition tasks correlates only for some but not all tasks to localization performance. This indicates a need for retrieval approaches specifically designed for localization tasks. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.