Title
Nonlocal Mumford-Shah regularizers for color image restoration.
Abstract
We propose here a class of restoration algorithms for color images, based upon the Mumford-Shah (MS) model and nonlocal image information. The Ambrosio-Tortorelli and Shah elliptic approximations are defined to work in a small local neighborhood, which are sufficient to denoise smooth regions with sharp boundaries. However, texture is nonlocal in nature and requires semilocal/non-local information for efficient image denoising and restoration. Inspired from recent works (nonlocal means of Buades, Coll, Morel, and nonlocal total variation of Gilboa, Osher), we extend the local Ambrosio-Tortorelli and Shah approximations to MS functional (MS) to novel nonlocal formulations, for better restoration of fine structures and texture. We present several applications of the proposed nonlocal MS regularizers in image processing such as color image denoising, color image deblurring in the presence of Gaussian or impulse noise, color image inpainting, color image super-resolution, and color filter array demosaicing. In all the applications, the proposed nonlocal regularizers produce superior results over the local ones, especially in image inpainting with large missing regions. We also prove several characterizations of minimizers based upon dual norm formulations.
Year
DOI
Venue
2011
10.1109/TIP.2010.2092433
IEEE Transactions on Image Processing
Keywords
Field
DocType
ambrosio-tortorelli elliptic approximations,novel nonlocal formulation,mumford-shah (ms) regularizer,efficient image denoising,deblurring,color image inpainting,image processing,color image restoration,inpainting,impulse noise,image inpainting,color image denoising,color image deblurring,color image,nonlocal operators,nonlocal mean,nonlocal mumford-shah regularizers,image denoising,image restoration,ambrosio-tortorelli approximations,demosaicing,super-resolution,denoising,color image super-resolution,mumford-shah model,nonlocal total variation,nonlocal image information,gaussian noise,proposed nonlocal ms regularizers,color array demosaicing,image colour analysis,noise reduction,color,colored noise,super resolution,total variation,noise,algorithms,colorimetry,color filter array,pixel,fine structure
Computer vision,Deblurring,Image processing,Demosaicing,Inpainting,Artificial intelligence,Image restoration,Color filter array,Image resolution,Mathematics,Color image
Journal
Volume
Issue
ISSN
20
6
1941-0042
Citations 
PageRank 
References 
46
1.19
53
Authors
4
Name
Order
Citations
PageRank
Miyoun Jung112510.72
Xavier Bresson2184268.08
Tony F. Chan360349.56
Luminita A. Vese45389302.64