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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2017 IEEE International Conference on Image Processing (ICIP) s. 2079 - 2083
Hlavní autoři:	Ma, Tian-Hui, Lou, Yifei, Huang, Ting-Zhu, Zhao, Xi-Le
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.09.2017
Témata:	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
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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