Structure-From-Motion with a Non-Parametric Camera Model
(2025) 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025 In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition p.1040-1049- Abstract
In this paper, we present a new generic Structure-From-Motion pipeline, GenSfM, that uses a non-parametric camera projection model. The model is self-calibrated during the reconstruction process and can fit a wide variety of cameras, ranging from simple low-distortion pinhole cameras to more extreme optical systems such as fisheye or catadioptric cameras. The key component in our framework is an adaptive calibration procedure that can estimate partial calibrations, only modeling regions of the image where sufficient constraints are available. In experiments, we show that our method achieves comparable accuracy to traditional Structure-From-Motion pipelines in easy scenarios, and outperforms them in cases where they are unable to... (More)
In this paper, we present a new generic Structure-From-Motion pipeline, GenSfM, that uses a non-parametric camera projection model. The model is self-calibrated during the reconstruction process and can fit a wide variety of cameras, ranging from simple low-distortion pinhole cameras to more extreme optical systems such as fisheye or catadioptric cameras. The key component in our framework is an adaptive calibration procedure that can estimate partial calibrations, only modeling regions of the image where sufficient constraints are available. In experiments, we show that our method achieves comparable accuracy to traditional Structure-From-Motion pipelines in easy scenarios, and outperforms them in cases where they are unable to self-calibrate their parametric models. Code is at https://github.com/Ivonne320/GenSfM.git
(Less)
- author
- Wang, Yihan ; Pan, Linfei ; Pollefeys, Marc and Larsson, Viktor LU
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- camera pose estimation, non-parametric camera model, sfm, triangulation
- host publication
- 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- series title
- Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- pages
- 10 pages
- conference name
- 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
- conference location
- Nashville, United States
- conference dates
- 2025-06-11 - 2025-06-15
- external identifiers
-
- scopus:105017068129
- ISSN
- 1063-6919
- ISBN
- 979-8-3315-4364-8
- DOI
- 10.1109/CVPR52734.2025.00105
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 IEEE.
- id
- 690bad4b-0988-4871-a56e-aa52531d79cc
- date added to LUP
- 2025-12-08 14:50:56
- date last changed
- 2025-12-09 08:23:57
@inproceedings{690bad4b-0988-4871-a56e-aa52531d79cc,
abstract = {{<p>In this paper, we present a new generic Structure-From-Motion pipeline, GenSfM, that uses a non-parametric camera projection model. The model is self-calibrated during the reconstruction process and can fit a wide variety of cameras, ranging from simple low-distortion pinhole cameras to more extreme optical systems such as fisheye or catadioptric cameras. The key component in our framework is an adaptive calibration procedure that can estimate partial calibrations, only modeling regions of the image where sufficient constraints are available. In experiments, we show that our method achieves comparable accuracy to traditional Structure-From-Motion pipelines in easy scenarios, and outperforms them in cases where they are unable to self-calibrate their parametric models. Code is at https://github.com/Ivonne320/GenSfM.git</p>}},
author = {{Wang, Yihan and Pan, Linfei and Pollefeys, Marc and Larsson, Viktor}},
booktitle = {{2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}},
isbn = {{979-8-3315-4364-8}},
issn = {{1063-6919}},
keywords = {{camera pose estimation; non-parametric camera model; sfm; triangulation}},
language = {{eng}},
pages = {{1040--1049}},
series = {{Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}},
title = {{Structure-From-Motion with a Non-Parametric Camera Model}},
url = {{http://dx.doi.org/10.1109/CVPR52734.2025.00105}},
doi = {{10.1109/CVPR52734.2025.00105}},
year = {{2025}},
}