TBPos: Dataset for Large-Scale Precision Visual Localization

Masud Fahim, Ilona Söchting, Luca Ferranti, Juho Kannala, Jani Boutellier*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review


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.

Original languageEnglish
Title of host publicationImage Analysis - Proceedings of SCIA 2023
EditorsRikke Gade, Michael Felsberg, Joni-Kristian Kämäräinen
Number of pages11
ISBN (Print)978-3-031-31434-6
Publication statusPublished - 2023
MoE publication typeA4 Conference publication
EventScandinavian Conference on Image Analysis - Levi, Kittilä, Finland
Duration: 18 Apr 202321 Apr 2023
Conference number: 23

Publication series

NameLecture Notes in Computer Science
Volume13885 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceScandinavian Conference on Image Analysis
Abbreviated titleSCIA


  • 6DoF pose
  • Computer vision
  • Dataset
  • Visual localization


Dive into the research topics of 'TBPos: Dataset for Large-Scale Precision Visual Localization'. Together they form a unique fingerprint.

Cite this