A Structure From Motion Pipeline for Orthographic Multi-View Images

Kai A. Neumann, Philipp P. Hoffmann, Max von Buelow, Volker Knauthe, Tristan Wirth, Christian Kontermann, Arjan Kuijper, Stefan Guthe, Dieter W. Fellner

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Structure from Motion (SfM) plays a crucial role in unstructured capturing. While images are usually taken by perspective cameras, orthographic camera projections do not suffer from the foreshortening effect, that leads to varying capturing quality in image regions. Most contributions to orthographic image SfM assume a perspective setup with nearly infinite focal length. These assumptions lead to potentially sub-optimal camera pose estimation. Therefore, we propose a SfM pipeline that is optimized for orthographically projected images. For this, we estimate initial camera poses using the factorization method by Tomasi and Kanade. These poses are further refined by a specialized bundle adjustment implementation for orthographic projections. The proposed pipeline surpasses the precision of state-of-the-art work by an order of magnitude, while consuming considerably less computational resources.
Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing: Proceedings
PublisherACM/IEEE
Pages1181-1185
Number of pages5
ISBN (Print)978-1-6654-9620-9
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Conference on Image Processing: ICIP 2022 - Bordeaux, France
Duration: 16 Oct 202219 Oct 2022

Conference

Conference2022 IEEE International Conference on Image Processing
Abbreviated titleICIP 2022
Country/TerritoryFrance
CityBordeaux
Period16/10/2219/10/22

Keywords

  • Structure-from-Motion (SfM)
  • Multi-view stereo
  • Input pipelines
  • Digitization and image capture

Fields of Expertise

  • Information, Communication & Computing

Fingerprint

Dive into the research topics of 'A Structure From Motion Pipeline for Orthographic Multi-View Images'. Together they form a unique fingerprint.

Cite this