Group-based truncated l1-2 model for image inpainting

We propose a novel image inpainting model that can effectively estimate missing pixels in an observed image. The latent image is characterized by a group-based low-rank prior, which assumes that a group of vectorized similar image patches can be well approximated by a low-rank matrix. We enforce the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2017 IEEE International Conference on Image Processing (ICIP) S. 2079 - 2083
Hauptverfasser: Ma, Tian-Hui, Lou, Yifei, Huang, Ting-Zhu, Zhao, Xi-Le
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.09.2017
Schlagworte:
Approximation algorithms
Computational modeling
Convergence
Convex functions
Difference of convex functions algorithm
image inpainting
l 1-2 minimization
low-rank matrix approximation
Mathematical model
Measurement
Minimization
nonlocal self-similarity
ISSN:2381-8549
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a novel image inpainting model that can effectively estimate missing pixels in an observed image. The latent image is characterized by a group-based low-rank prior, which assumes that a group of vectorized similar image patches can be well approximated by a low-rank matrix. We enforce the low-rankness of each group by penalizing a truncated difference of the l 1 and the l 2 norms of its singular values, which achieves a close approximation to the matrix rank. We apply a difference of convex algorithm (DCA) to solve the proposed model efficiently. Our method is validated on filling missing blocks and randomly missing pixels, with superior performance over the state-of-the-art.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296648