Investigating the Role of Image Retrieval for Visual Localization An Exhaustive Benchmark

• Published in: International journal of computer vision Vol. 130; no. 7; pp. 1811 - 1836
• Main Authors: Humenberger, Martin, Cabon, Yohann, Pion, Noé, Weinzaepfel, Philippe, Lee, Donghwan, Guérin, Nicolas, Sattler, Torsten, Csurka, Gabriela
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2022
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Image Processing and Computer Vision; Pattern Recognition; Pattern Recognition and Graphics; S.I. : 3D Computer Vision; Vision; Benchmark; Place recognition; Landmark retrieval; Visual localization; Image retrieval; Camera pose estimation
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-022-01615-7

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 purposes: (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 both of them. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes which often differs from the requirements of visual localization. In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms. First, we introduce a novel benchmark setup and compare state-of-the-art retrieval representations on multiple datasets using localization performance as metric. Second, we investigate several definitions of “ground truth” for image retrieval. Using these definitions as upper bounds for the visual localization paradigms, we show that there is still significant room for improvement. Third, using these tools and in-depth analysis, we show that retrieval performance on classical landmark retrieval or place recognition tasks correlates only for some but not all paradigms to localization performance. Finally, we analyze the effects of blur and dynamic scenes in the images. We conclude that there is a need for retrieval approaches specifically designed for localization paradigms. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization .