Revealing and modifying non-local variations in a single image

Tali Dekel; Tomer Michaeli; Michal Irani; William T. Freeman

doi:10.1145/2816795.2818113

Revealing and modifying non-local variations in a single image

Tali Dekel, Tomer Michaeli, Michal Irani, William T. Freeman

Weizmann Institute of Science, Technion - Israel Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

We present an algorithm for automatically detecting and visualizing small non-local variations between repeating structures in a single image. Our method allows to automatically correct these variations, thus producing an 'idealized' version of the image in which the resemblance between recurring structures is stronger. Alternatively, it can be used to magnify these variations, thus producing an exaggerated image which highlights the various variations that are difficult to spot in the input image. We formulate the estimation of deviations from perfect recurrence as a general optimization problem, and demonstrate it in the particular cases of geometric deformations and color variations.

Original language	English
Article number	227
Journal	ACM Transactions on Graphics
Volume	34
Issue number	6
DOIs	https://doi.org/10.1145/2816795.2818113
State	Published - Oct 2015

Keywords

Defects
Deformations
Distortions
Internal patch recurrence
Irregularities

All Science Journal Classification (ASJC) codes

Computer Graphics and Computer-Aided Design

Access to Document

10.1145/2816795.2818113

http://hdl.handle.net/1721.1/99936License: Unspecified

Cite this

@article{9a0979968a154a4488c7d012bc68af80,

title = "Revealing and modifying non-local variations in a single image",

abstract = "We present an algorithm for automatically detecting and visualizing small non-local variations between repeating structures in a single image. Our method allows to automatically correct these variations, thus producing an 'idealized' version of the image in which the resemblance between recurring structures is stronger. Alternatively, it can be used to magnify these variations, thus producing an exaggerated image which highlights the various variations that are difficult to spot in the input image. We formulate the estimation of deviations from perfect recurrence as a general optimization problem, and demonstrate it in the particular cases of geometric deformations and color variations.",

keywords = "Defects, Deformations, Distortions, Internal patch recurrence, Irregularities",

author = "Tali Dekel and Tomer Michaeli and Michal Irani and Freeman, {William T.}",

note = "Publisher Copyright: Copyright {\textcopyright} 2015 ACM.",

year = "2015",

month = oct,

doi = "10.1145/2816795.2818113",

language = "الإنجليزيّة",

volume = "34",

journal = "ACM Transactions on Graphics",

issn = "0730-0301",

publisher = "Association for Computing Machinery (ACM)",

number = "6",

}

TY - JOUR

T1 - Revealing and modifying non-local variations in a single image

AU - Dekel, Tali

AU - Michaeli, Tomer

AU - Irani, Michal

AU - Freeman, William T.

PY - 2015/10

Y1 - 2015/10

N2 - We present an algorithm for automatically detecting and visualizing small non-local variations between repeating structures in a single image. Our method allows to automatically correct these variations, thus producing an 'idealized' version of the image in which the resemblance between recurring structures is stronger. Alternatively, it can be used to magnify these variations, thus producing an exaggerated image which highlights the various variations that are difficult to spot in the input image. We formulate the estimation of deviations from perfect recurrence as a general optimization problem, and demonstrate it in the particular cases of geometric deformations and color variations.

AB - We present an algorithm for automatically detecting and visualizing small non-local variations between repeating structures in a single image. Our method allows to automatically correct these variations, thus producing an 'idealized' version of the image in which the resemblance between recurring structures is stronger. Alternatively, it can be used to magnify these variations, thus producing an exaggerated image which highlights the various variations that are difficult to spot in the input image. We formulate the estimation of deviations from perfect recurrence as a general optimization problem, and demonstrate it in the particular cases of geometric deformations and color variations.

KW - Defects

KW - Deformations

KW - Distortions

KW - Internal patch recurrence

KW - Irregularities

UR - http://www.scopus.com/inward/record.url?scp=84996525915&partnerID=8YFLogxK

U2 - 10.1145/2816795.2818113

DO - 10.1145/2816795.2818113

M3 - مقالة

SN - 0730-0301

VL - 34

JO - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

IS - 6

M1 - 227

ER -

Revealing and modifying non-local variations in a single image

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this