TBPos: Dataset for Large-Scale Precision Visual Localization

TL;DR

TBPos is a new large-scale dataset for visual localization that provides highly accurate ground truth poses by deriving both database and query images from the same laser scanner data, facilitating improved evaluation of localization algorithms.

Contribution

The paper introduces TBPos, a large-scale dataset with precise ground truth poses for visual localization, derived from the same laser scanner data for both database and query images.

Findings

TBPos enables more accurate evaluation of localization algorithms.

The dataset covers diverse large-scale environments.

Experimental results demonstrate the dataset's effectiveness.

Abstract

Image based localization is a classical computer vision challenge, with several well-known datasets. Generally, datasets consist of a visual 3D database that captures the modeled scenery, as well as query images whose 3D pose is to be discovered. Usually the query images have been acquired with a camera that differs from the imaging hardware used to collect the 3D database; consequently, it is hard to acquire accurate ground truth poses between query images and the 3D database. As the accuracy of visual localization algorithms constantly improves, precise ground truth becomes increasingly important. This paper proposes TBPos, a novel large-scale visual dataset for image based positioning, which provides query images with fully accurate ground truth poses: both the database images and the query images have been derived from the same laser scanner data. In the experimental part of the paper, the proposed dataset is evaluated by means of an image-based localization pipeline.