Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Image Stitching with Locally Shared Rotation Axis

Barath, Daniel ; Ding, Yaqing LU ; Kukelova, Zuzana and Larsson, Viktor LU (2021) 9th International Conference on 3D Vision, 3DV 2021 p.1382-1391
Abstract
We consider the problem of stitching image sequences with cameras undergoing pure rotational motion. We leverage the assumption of a locally constant rotation axis, i.e., neighboring frames have a shared but unknown rotation axis. This assumption holds in many common image capturing scenarios, e.g., panoramic sweeping motions. Using this additional constraint, we develop techniques for three-view camera rotation estimation; a minimal solver for the two-view estimation with a known rotation axis; and a globally optimal robust estimator for the two-view case. We show on publicly available datasets that the proposed methods lead to camera rotation estimation superior to the state-of-the-art in terms of accuracy with comparable run-time. The... (More)
We consider the problem of stitching image sequences with cameras undergoing pure rotational motion. We leverage the assumption of a locally constant rotation axis, i.e., neighboring frames have a shared but unknown rotation axis. This assumption holds in many common image capturing scenarios, e.g., panoramic sweeping motions. Using this additional constraint, we develop techniques for three-view camera rotation estimation; a minimal solver for the two-view estimation with a known rotation axis; and a globally optimal robust estimator for the two-view case. We show on publicly available datasets that the proposed methods lead to camera rotation estimation superior to the state-of-the-art in terms of accuracy with comparable run-time. The source code will be made available. (Less)
Please use this url to cite or link to this publication:
author
; ; and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2021 International Conference on 3D Vision (3DV)
pages
10 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
9th International Conference on 3D Vision, 3DV 2021
conference location
Virtual, Online, United Kingdom
conference dates
2021-12-01 - 2021-12-03
external identifiers
  • scopus:85125007690
ISBN
978-1-6654-2689-3
978-1-6654-2688-6
DOI
10.1109/3DV53792.2021.00145
language
English
LU publication?
no
id
353622ae-1ba2-44bb-aedb-1bfc58239521
date added to LUP
2022-09-06 13:23:07
date last changed
2025-04-04 15:29:20
@inproceedings{353622ae-1ba2-44bb-aedb-1bfc58239521,
  abstract     = {{We consider the problem of stitching image sequences with cameras undergoing pure rotational motion. We leverage the assumption of a locally constant rotation axis, i.e., neighboring frames have a shared but unknown rotation axis. This assumption holds in many common image capturing scenarios, e.g., panoramic sweeping motions. Using this additional constraint, we develop techniques for three-view camera rotation estimation; a minimal solver for the two-view estimation with a known rotation axis; and a globally optimal robust estimator for the two-view case. We show on publicly available datasets that the proposed methods lead to camera rotation estimation superior to the state-of-the-art in terms of accuracy with comparable run-time. The source code will be made available.}},
  author       = {{Barath, Daniel and Ding, Yaqing and Kukelova, Zuzana and Larsson, Viktor}},
  booktitle    = {{2021 International Conference on 3D Vision (3DV)}},
  isbn         = {{978-1-6654-2689-3}},
  language     = {{eng}},
  pages        = {{1382--1391}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Image Stitching with Locally Shared Rotation Axis}},
  url          = {{http://dx.doi.org/10.1109/3DV53792.2021.00145}},
  doi          = {{10.1109/3DV53792.2021.00145}},
  year         = {{2021}},
}