Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression

Image super-resolution (SR) reconstruction is essentially an ill-posed problem, so it is important to design an effective prior. For this purpose, we propose a novel image SR method by learning both non-local and local regularization priors from a given low-resolution image. The non-local prior take...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing 2012-11, Vol.21 (11), p.4544-4556
Hauptverfasser:	Zhang, Kaibing, Gao, Xinbo, Tao, Dacheng, Li, Xuelong
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Animals Applied sciences Artificial Intelligence Databases, Factual Detection, estimation, filtering, equalization, prediction Exact sciences and technology Humans Image processing Image Processing, Computer-Assisted - methods Image reconstruction Image resolution Image super-resolution Information, signal and communications theory Interpolation Kernel non-local means Pattern Recognition, Automated - methods PSNR Regression Analysis regularization prior Reproducibility of Results self-similarity Signal and communications theory Signal processing Signal, noise steering kernel regression Strontium Telecommunications and information theory Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!