Example-Based Learning for Single-Image Super-Resolution

Kim, KI; Kwon, Y

doi:10.1007/978-3-540-69321-5_46

Datensatz

DATENSATZ AKTIONENEXPORT

Zur Ablage hinzufügen

Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben

Konferenzbeitrag

Example-Based Learning for Single-Image Super-Resolution

MPG-Autoren

/persons/resource/persons84014

Kim, KI
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Externe Ressourcen

https://link.springer.com/content/pdf/10.1007%2F978-3-540-69321-5_46.pdf
(Verlagsversion)

Volltexte (beschränkter Zugriff)

Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.

Volltexte (frei zugänglich)

Es sind keine frei zugänglichen Volltexte in PuRe verfügbar

Ergänzendes Material (frei zugänglich)

Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar

Zitation

Kim, K., & Kwon, Y. (2008). Example-Based Learning for Single-Image Super-Resolution. In G. Rigoll (Ed.), Pattern Recognition: 30th DAGM Symposium Munich, Germany, June 10-13, 2008 (pp. 456-463). Berlin, Germany: Springer.

Zitierlink: https://hdl.handle.net/11858/00-001M-0000-0013-C8FB-F

Zusammenfassung

This paper proposes a regression-based method for single-image super-resolution. Kernel ridge regression (KRR) is used to estimate the high-frequency details of the underlying high-resolution image. A sparse solution of KRR is found by combining the ideas of kernel matching pursuit and gradient descent, which allows time-complexity to be kept to a moderate level. To resolve the problem of ringing artifacts occurring due to the regularization effect, the regression results are post-processed using a prior model of a generic image class. Experimental results demonstrate the effectiveness of the proposed method.