Sparse–View Localization via Online Neural 3D Regression
(2026) p.21794-21804- Abstract
- We present ON3R, an online-trained neural regressor addressing sparse-view structureless localization, where database images have limited visual overlap and no prebuilt 3D map. Given any sparse matches between a query and a K-tuple of posed database views, ON3R predicts 3D coordinates for matched query keypoints, supervised by database reprojection residuals and a monocular depth prior. Afterwards, the absolute pose of the query is estimated via P3P-RANSAC and refined with lightweight bundle adjustment. Across MegaDepth, Cambridge Landmarks, and a sparsified version of Aachen Day-Night, ON3R outperforms existing methods. ON3R is particularly effective when the data is extremely sparse – we focus on K ≤ 10 database images. The code is... (More)
- We present ON3R, an online-trained neural regressor addressing sparse-view structureless localization, where database images have limited visual overlap and no prebuilt 3D map. Given any sparse matches between a query and a K-tuple of posed database views, ON3R predicts 3D coordinates for matched query keypoints, supervised by database reprojection residuals and a monocular depth prior. Afterwards, the absolute pose of the query is estimated via P3P-RANSAC and refined with lightweight bundle adjustment. Across MegaDepth, Cambridge Landmarks, and a sparsified version of Aachen Day-Night, ON3R outperforms existing methods. ON3R is particularly effective when the data is extremely sparse – we focus on K ≤ 10 database images. The code is available athttps://github.com/ludvigdillen/ON3R. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/c86c10b3-6b3a-4dda-abc8-37a7ab8402ad
- author
- Dillén, Ludvig
LU
; Oskarsson, Magnus
LU
and Larsson, Viktor
LU
- organization
- publishing date
- 2026
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Pose estimation, localization
- host publication
- Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- pages
- 11 pages
- publisher
- IEEE Computer Society
- language
- English
- LU publication?
- yes
- id
- c86c10b3-6b3a-4dda-abc8-37a7ab8402ad
- alternative location
- https://openaccess.thecvf.com/content/CVPR2026/papers/Dillen_Sparse-View_Localization_via_Online_Neural_3D_Regression_CVPR_2026_paper.pdf
- date added to LUP
- 2026-06-26 12:36:05
- date last changed
- 2026-09-23 13:19:01
@inproceedings{c86c10b3-6b3a-4dda-abc8-37a7ab8402ad,
abstract = {{We present ON3R, an online-trained neural regressor addressing sparse-view structureless localization, where database images have limited visual overlap and no prebuilt 3D map. Given any sparse matches between a query and a K-tuple of posed database views, ON3R predicts 3D coordinates for matched query keypoints, supervised by database reprojection residuals and a monocular depth prior. Afterwards, the absolute pose of the query is estimated via P3P-RANSAC and refined with lightweight bundle adjustment. Across MegaDepth, Cambridge Landmarks, and a sparsified version of Aachen Day-Night, ON3R outperforms existing methods. ON3R is particularly effective when the data is extremely sparse – we focus on K ≤ 10 database images. The code is available athttps://github.com/ludvigdillen/ON3R.}},
author = {{Dillén, Ludvig and Oskarsson, Magnus and Larsson, Viktor}},
booktitle = {{Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}},
keywords = {{Pose estimation; localization}},
language = {{eng}},
pages = {{21794--21804}},
publisher = {{IEEE Computer Society}},
title = {{Sparse–View Localization via Online Neural 3D Regression}},
url = {{https://openaccess.thecvf.com/content/CVPR2026/papers/Dillen_Sparse-View_Localization_via_Online_Neural_3D_Regression_CVPR_2026_paper.pdf}},
year = {{2026}},
}