Privacy Preserving Localization via Coordinate Permutations
(2023) 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 In Proceedings of the IEEE International Conference on Computer Vision p.18128-18137- Abstract
Recent methods on privacy-preserving image-based localization use a random line parameterization to protect the privacy of query images and database maps. The lifting of points to lines effectively drops one of the two geometric constraints traditionally used with point-to-point correspondences in structure-based localization. This leads to a significant loss of accuracy for the privacy-preserving methods. In this paper, we overcome this limitation by devising a coordinate permutation scheme that allows for recovering the original point positions during pose estimation. The recovered points provide the full 2D geometric constraints and enable us to close the gap between privacy-preserving and traditional methods in terms of accuracy.... (More)
Recent methods on privacy-preserving image-based localization use a random line parameterization to protect the privacy of query images and database maps. The lifting of points to lines effectively drops one of the two geometric constraints traditionally used with point-to-point correspondences in structure-based localization. This leads to a significant loss of accuracy for the privacy-preserving methods. In this paper, we overcome this limitation by devising a coordinate permutation scheme that allows for recovering the original point positions during pose estimation. The recovered points provide the full 2D geometric constraints and enable us to close the gap between privacy-preserving and traditional methods in terms of accuracy. Another limitation of random line methods is their vulnerability to density based 3D line cloud inversion attacks. Our method not only provides better accuracy than the original random line based approach but also provides stronger privacy guarantees against these recently proposed attacks. Extensive experiments on standard benchmark datasets demonstrate these improvements consistently across both scenarios of protecting the privacy of query images as well as the database map.
(Less)
- author
- Pan, Linfei ; Schönberger, Johannes L. ; Larsson, Viktor LU and Pollefeys, Marc
- organization
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the IEEE International Conference on Computer Vision
- series title
- Proceedings of the IEEE International Conference on Computer Vision
- pages
- 10 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
- conference location
- Paris, France
- conference dates
- 2023-10-02 - 2023-10-06
- external identifiers
-
- scopus:85185876145
- ISSN
- 1550-5499
- ISBN
- 9798350307184
- DOI
- 10.1109/ICCV51070.2023.01666
- language
- English
- LU publication?
- yes
- id
- 22246c7b-cf43-4ab8-bdca-5c131fe63594
- date added to LUP
- 2024-03-18 15:23:21
- date last changed
- 2024-03-18 15:24:15
@inproceedings{22246c7b-cf43-4ab8-bdca-5c131fe63594, abstract = {{<p>Recent methods on privacy-preserving image-based localization use a random line parameterization to protect the privacy of query images and database maps. The lifting of points to lines effectively drops one of the two geometric constraints traditionally used with point-to-point correspondences in structure-based localization. This leads to a significant loss of accuracy for the privacy-preserving methods. In this paper, we overcome this limitation by devising a coordinate permutation scheme that allows for recovering the original point positions during pose estimation. The recovered points provide the full 2D geometric constraints and enable us to close the gap between privacy-preserving and traditional methods in terms of accuracy. Another limitation of random line methods is their vulnerability to density based 3D line cloud inversion attacks. Our method not only provides better accuracy than the original random line based approach but also provides stronger privacy guarantees against these recently proposed attacks. Extensive experiments on standard benchmark datasets demonstrate these improvements consistently across both scenarios of protecting the privacy of query images as well as the database map.</p>}}, author = {{Pan, Linfei and Schönberger, Johannes L. and Larsson, Viktor and Pollefeys, Marc}}, booktitle = {{Proceedings of the IEEE International Conference on Computer Vision}}, isbn = {{9798350307184}}, issn = {{1550-5499}}, language = {{eng}}, pages = {{18128--18137}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{Proceedings of the IEEE International Conference on Computer Vision}}, title = {{Privacy Preserving Localization via Coordinate Permutations}}, url = {{http://dx.doi.org/10.1109/ICCV51070.2023.01666}}, doi = {{10.1109/ICCV51070.2023.01666}}, year = {{2023}}, }