Partially calibrated semi-generalized pose from hybrid point correspondences
(2023) 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 p.2881-2890- Abstract
We study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set of 2D-2D and 2D-3D point correspondences. We study all possible camera configurations within the generalized camera system. To derive practical solvers to previously unsolved challenging configurations, we test different parameterizations as well as different solving strategies based on state-of-the-art methods for generating efficient polynomial solvers. We evaluate the three most promising solvers, i.e., the H51f solver with five 2D-2D correspondences and one 2D-3D match viewed by the same camera inside the generalized camera, the... (More)
We study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set of 2D-2D and 2D-3D point correspondences. We study all possible camera configurations within the generalized camera system. To derive practical solvers to previously unsolved challenging configurations, we test different parameterizations as well as different solving strategies based on state-of-the-art methods for generating efficient polynomial solvers. We evaluate the three most promising solvers, i.e., the H51f solver with five 2D-2D correspondences and one 2D-3D match viewed by the same camera inside the generalized camera, the H32f solver with three 2D-2D and two 2D-3D correspondences, and the H13f solver with one 2D-2D and three 2D-3D matches, on synthetic and real data. We show that in the presence of noise in the 3D points these solvers provide better estimates than the corresponding absolute pose solvers.
(Less)
- author
- Bhayani, Snehal ; Sattler, Torsten ; Larsson, Viktor LU ; Heikkila, Janne and Kukelova, Zuzana
- organization
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Algorithms: 3D computer vision, Computational photography, image and video synthesis, Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)
- host publication
- Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
- pages
- 10 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
- conference location
- Waikoloa, United States
- conference dates
- 2023-01-03 - 2023-01-07
- external identifiers
-
- scopus:85149009348
- ISBN
- 9781665493468
- DOI
- 10.1109/WACV56688.2023.00290
- language
- English
- LU publication?
- yes
- id
- 80acb7ec-3aff-4ba3-a10e-82950c3195ae
- date added to LUP
- 2023-03-16 14:54:39
- date last changed
- 2023-11-21 02:12:20
@inproceedings{80acb7ec-3aff-4ba3-a10e-82950c3195ae,
abstract = {{<p>We study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set of 2D-2D and 2D-3D point correspondences. We study all possible camera configurations within the generalized camera system. To derive practical solvers to previously unsolved challenging configurations, we test different parameterizations as well as different solving strategies based on state-of-the-art methods for generating efficient polynomial solvers. We evaluate the three most promising solvers, i.e., the H51f solver with five 2D-2D correspondences and one 2D-3D match viewed by the same camera inside the generalized camera, the H32f solver with three 2D-2D and two 2D-3D correspondences, and the H13f solver with one 2D-2D and three 2D-3D matches, on synthetic and real data. We show that in the presence of noise in the 3D points these solvers provide better estimates than the corresponding absolute pose solvers.</p>}},
author = {{Bhayani, Snehal and Sattler, Torsten and Larsson, Viktor and Heikkila, Janne and Kukelova, Zuzana}},
booktitle = {{Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023}},
isbn = {{9781665493468}},
keywords = {{Algorithms: 3D computer vision; Computational photography; image and video synthesis; Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)}},
language = {{eng}},
pages = {{2881--2890}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
title = {{Partially calibrated semi-generalized pose from hybrid point correspondences}},
url = {{http://dx.doi.org/10.1109/WACV56688.2023.00290}},
doi = {{10.1109/WACV56688.2023.00290}},
year = {{2023}},
}