Neumann, Kai A. ; Hoffmann, Philipp P. ; Buelow, Max von ; Knauthe, Volker ; Wirth, Tristan ; Kontermann, Christian ; Kuijper, Arjan ; Guthe, Stefan ; Fellner, Dieter W. (2022)
A Structure From Motion Pipeline for Orthographic Multi-View Images.
29th IEEE International Conference on Image Processing (ICIP'22). Bordeaux, France (16.10.2022-19.10.2022)
doi: 10.1109/ICIP46576.2022.9897368
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Neumann, Kai A. ; Hoffmann, Philipp P. ; Buelow, Max von ; Knauthe, Volker ; Wirth, Tristan ; Kontermann, Christian ; Kuijper, Arjan ; Guthe, Stefan ; Fellner, Dieter W. |
| Art des Eintrags: | Bibliographie |
| Titel: | A Structure From Motion Pipeline for Orthographic Multi-View Images |
| Sprache: | Englisch |
| Publikationsjahr: | 18 Oktober 2022 |
| Verlag: | IEEE |
| Buchtitel: | 2022 IEEE International Conference on Image Processing: Proceedings |
| Veranstaltungstitel: | 29th IEEE International Conference on Image Processing (ICIP'22) |
| Veranstaltungsort: | Bordeaux, France |
| Veranstaltungsdatum: | 16.10.2022-19.10.2022 |
| DOI: | 10.1109/ICIP46576.2022.9897368 |
| Kurzbeschreibung (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. |
| Freie Schlagworte: | Structure-from-Motion (SfM), Multi-view stereo, Input pipelines, Digitization and image capture |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 24 Nov 2022 08:34 |
| Letzte Änderung: | 23 Feb 2023 13:49 |
| PPN: | 505271788 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum