Fast Relative Pose Estimation using Relative Depth
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00380521" target="_blank" >RIV/68407700:21230/24:00380521 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/3DV62453.2024.00053" target="_blank" >https://doi.org/10.1109/3DV62453.2024.00053</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/3DV62453.2024.00053" target="_blank" >10.1109/3DV62453.2024.00053</a>
Alternative languages
Result language
angličtina
Original language name
Fast Relative Pose Estimation using Relative Depth
Original language description
In this paper, we revisit the problem of estimating the relative pose from a sparse set of point-correspondences. For each point-correspondence we also estimate the relative depth, i.e. the relative distance to the scene point in the two images. This yields an additional constraint, allowing us to use fewer matches in RANSAC to generate the pose candidates. In the paper we propose two novel minimal solvers: one for general motion and one for the case of known vertical direction. To obtain the relative depth estimates, we explore using scale estimates obtained from a keypoint detector as well as a neural network that directly predicts the relative depth for a pair of patches. We show in experiments that while our estimates are more noisy compared to the purely point-based solvers, the smaller sample size leads to a significantly reduced runtime in settings with high outlier ratios.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
3DV2024: Proceedings of the 2024 International Conference in 3D Vision
ISBN
979-8-3503-6246-6
ISSN
2378-3826
e-ISSN
2475-7888
Number of pages
9
Pages from-to
873-881
Publisher name
IEEE Computer Society
Place of publication
Los Alamitos
Event location
Davos
Event date
Mar 18, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001250581700071