Hallucinating Face Image by Regularization Models in High-Resolution Feature Space

In this paper, we propose two novel regularization models in patch-wise and pixel-wise, respectively, which are efficient to reconstruct high-resolution (HR) face image from low-resolution (LR) input. Unlike the conventional patch-based models which depend on the assumption of local geometry consist...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2018-06, Vol.27 (6), p.2980-2995
Hauptverfasser:	Shi, Jingang, Liu, Xin, Zong, Yuan, Qi, Chun, Zhao, Guoying
Format:	Artikel
Sprache:	eng
Schlagworte:	Face Face hallucination Geometry Image edge detection Image reconstruction Image resolution Kernel kernel method manifold learning regularization framework super-resolution Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!