Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
EndNote (UTF-8)
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database

Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., & Harmeling, S. (2012). Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database. In A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, & C. Schmid (Eds.), Computer Vision - ECCV 2012 (pp. 27-40). Berlin, Germany: Springer.

Item is

 

einblenden: alle

Basisdaten

ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-0001-8B3F-D Versions-Permalink: https://hdl.handle.net/21.11116/0000-000C-94C3-0
Genre: Konferenzbeitrag

Externe Referenzen

ausblenden:
externe Referenz:
https://link.springer.com/content/pdf/10.1007%2F978-3-642-33786-4_3.pdf (Verlagsversion)
Beschreibung:
-
OA-Status:
Keine Angabe

Urheber

ausblenden:
 Urheber:
Köhler, R1, Autor           
Hirsch, M1, Autor           
Mohler, BJ1, 2, Autor           
Schölkopf, B1, Autor                 
Harmeling, S1, Autor           
Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              
2Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              

Inhalt

ausblenden:
Schlagwörter: Abt. Schölkopf
 Zusammenfassung: Motion blur due to camera shake is one of the predominant sources of degradation in handheld photography. Single image blind deconvolution (BD) or motion deblurring aims at restoring a sharp latent image from the blurred recorded picture without knowing the camera motion that took place during the exposure. BD is a long-standing problem, but has attracted much attention recently, cumulating in several algorithms able to restore photos degraded by real camera motion in high quality. In this paper, we present a benchmark dataset for motion deblurring that allows quantitative performance evaluation and comparison of recent approaches featuring non-uniform blur models. To this end, we record and analyse real camera motion, which is played back on a robot platform such that we can record a sequence of sharp images sampling the six dimensional camera motion trajectory. The goal of deblurring is to recover one of these sharp images, and our dataset contains all information to assess how closely various algorithms approximate that goal. In a comprehensive comparison, we evaluate state-of-the-art single image BD algorithms incorporating uniform and non-uniform blur models.

Details

ausblenden:
Sprache(n):
 Datum: 2012-10
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1007/978-3-642-33786-4_3
BibTex Citekey: KohlerHMSHC2012
 Art des Abschluß: -

Veranstaltung

ausblenden:
Titel: 12th European Conference on Computer Vision (ECCV 2012)
Veranstaltungsort: Firenze, Italy
Start-/Enddatum: 2012-10-07 - 2012-10-13

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

ausblenden:
Titel: Computer Vision - ECCV 2012
Genre der Quelle: Konferenzband
 Urheber:
Fitzgibbon, A, Herausgeber
Lazebnik, S, Herausgeber
Perona, P, Herausgeber
Sato, Y, Herausgeber
Schmid, C, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: Berlin, Germany : Springer
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 27 - 40 Identifikator: ISBN: 978-3-642-33785-7

Quelle 2

ausblenden:
Titel: Lecture Notes in Computer Science
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 7578 Artikelnummer: - Start- / Endseite: - Identifikator: -