|Eric Brachmann, Martin Humenberger, Carsten Rother, Torsten Sattler|
|International Conference on Computer Vision (ICCV), virtual event, 11 - 17 October, 2021|
Visual camera re-localization is the task of estimating the camera pose of an image wrt a known scene. Benchmark datasets measuring camera pose accuracy have driven progress in the field. Due to the complexity of obtaining poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular choices for reference algorithms include Structure-from-Motion (SfM) or Simultaneous-Localization-and-Mapping (SLAM) using additional sensor input like depth measurements if available. Re-localization benchmarks thus measure how well a re-localization method replicates the results of the reference algorithm. This begs the question whether the choice of the reference algorithm favours a certain family of re-localization methods. In this paper, we analyze two widely used small-scale re-localization datasets. We show that evaluation outcomes indeed vary with the choice of the reference algorithm. As a result, we question common beliefs in re-localization literature, namely that learning-based scene coordinate regression outperforms classical feature-based methods, and that RGB-D-based methods outperform RGB-based methods. We argue that any claims on ranking re-localization methods should take accuracy and type of the reference algorithm into account.
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
FunctionalThis website uses functional cookies which are required for the search function to work and to apply for jobs and internships.
AnalyticalOur website uses analytical cookies to make it possible to analyse our website and optimize its usability.
Social mediaOur website places social media cookies to show YouTube and Vimeo videos. Cookies placed by these sites may track your personal data.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.