Goesele, Michael ; Snavely, Noah ; Curless, Brian ; Hoppe, Hugues ; Seitz, Steven M. (2007)
Multi-View Stereo for Community Photo Collections.
IEEE 11th International Conference on Computer Vision. Rio de Janeiro, Brasil (14.10.2007-20.10.2007)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is to intelligently choose images to match, both at a per-view and per-pixel level. We show that such adaptive view selection enables robust performance even with dramatic appearance variability. The stereo matching technique takes as input sparse 3D points reconstructed from structure-from-motion methods and iteratively grows surfaces from these points. Optimizing for surface normals within a photoconsistency measure significantly improves the matching results. While the focus of our approach is to estimate high-quality depth maps, we also show examples of merging the resulting depth maps into compelling scene reconstructions. We demonstrate our algorithm on standard multi-view stereo datasets and on casually acquired photo collections of famous scenes gathered from the Internet.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2007 |
| Autor(en): | Goesele, Michael ; Snavely, Noah ; Curless, Brian ; Hoppe, Hugues ; Seitz, Steven M. |
| Art des Eintrags: | Bibliographie |
| Titel: | Multi-View Stereo for Community Photo Collections |
| Sprache: | Englisch |
| Publikationsjahr: | 2007 |
| Veranstaltungstitel: | IEEE 11th International Conference on Computer Vision |
| Veranstaltungsort: | Rio de Janeiro, Brasil |
| Veranstaltungsdatum: | 14.10.2007-20.10.2007 |
| URL / URN: | http://download.hrz.tu-darmstadt.de/media/FB20/GCC/paper/Goe... |
| Kurzbeschreibung (Abstract): | We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is to intelligently choose images to match, both at a per-view and per-pixel level. We show that such adaptive view selection enables robust performance even with dramatic appearance variability. The stereo matching technique takes as input sparse 3D points reconstructed from structure-from-motion methods and iteratively grows surfaces from these points. Optimizing for surface normals within a photoconsistency measure significantly improves the matching results. While the focus of our approach is to estimate high-quality depth maps, we also show examples of merging the resulting depth maps into compelling scene reconstructions. We demonstrate our algorithm on standard multi-view stereo datasets and on casually acquired photo collections of famous scenes gathered from the Internet. |
| Freie Schlagworte: | Forschungsgruppe Capturing Reality (CARE), Computer vision, Multi-view stereo, Internet, Community photo collections, Depth maps |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphics, Capture and Massively Parallel Computing 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 16 Apr 2018 09:03 |
| Letzte Änderung: | 09 Dez 2021 11:46 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum