Transformation guided image completion

Jia Bin Huang, Johannes Kopf, Narendra Ahuja, Sing Bing Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we describe a new interactive image completion system that allows users to easily specify various forms of mid-level structures in the image. Our system supports the specification of four basic symmetric types: reflection, translation, rotation, and glide. The user inputs are automatically converted into guidance maps that encode possible candidate shifts and, indirectly, local transformations of rotation and scale. These guidance maps are used in conjunction with a color matching cost for image completion. We show that our system is capable of handling a variety of challenging examples.

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Computational Photography, ICCP 2013
DOIs
StatePublished - Aug 8 2013
Event2013 5th IEEE International Conference on Computational Photography, ICCP 2013 - Cambridge, MA, United States
Duration: Apr 19 2013Apr 21 2013

Publication series

Name2013 IEEE International Conference on Computational Photography, ICCP 2013

Other

Other2013 5th IEEE International Conference on Computational Photography, ICCP 2013
CountryUnited States
CityCambridge, MA
Period4/19/134/21/13

Fingerprint

Color matching
Specifications
Costs

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Vision and Pattern Recognition

Cite this

Huang, J. B., Kopf, J., Ahuja, N., & Kang, S. B. (2013). Transformation guided image completion. In 2013 IEEE International Conference on Computational Photography, ICCP 2013 [6528313] (2013 IEEE International Conference on Computational Photography, ICCP 2013). https://doi.org/10.1109/ICCPhot.2013.6528313

Transformation guided image completion. / Huang, Jia Bin; Kopf, Johannes; Ahuja, Narendra; Kang, Sing Bing.

2013 IEEE International Conference on Computational Photography, ICCP 2013. 2013. 6528313 (2013 IEEE International Conference on Computational Photography, ICCP 2013).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, JB, Kopf, J, Ahuja, N & Kang, SB 2013, Transformation guided image completion. in 2013 IEEE International Conference on Computational Photography, ICCP 2013., 6528313, 2013 IEEE International Conference on Computational Photography, ICCP 2013, 2013 5th IEEE International Conference on Computational Photography, ICCP 2013, Cambridge, MA, United States, 4/19/13. https://doi.org/10.1109/ICCPhot.2013.6528313
Huang JB, Kopf J, Ahuja N, Kang SB. Transformation guided image completion. In 2013 IEEE International Conference on Computational Photography, ICCP 2013. 2013. 6528313. (2013 IEEE International Conference on Computational Photography, ICCP 2013). https://doi.org/10.1109/ICCPhot.2013.6528313
Huang, Jia Bin ; Kopf, Johannes ; Ahuja, Narendra ; Kang, Sing Bing. / Transformation guided image completion. 2013 IEEE International Conference on Computational Photography, ICCP 2013. 2013. (2013 IEEE International Conference on Computational Photography, ICCP 2013).
@inproceedings{fc76ed6098c14a2087035f0f9d3b6d67,
title = "Transformation guided image completion",
abstract = "In this paper, we describe a new interactive image completion system that allows users to easily specify various forms of mid-level structures in the image. Our system supports the specification of four basic symmetric types: reflection, translation, rotation, and glide. The user inputs are automatically converted into guidance maps that encode possible candidate shifts and, indirectly, local transformations of rotation and scale. These guidance maps are used in conjunction with a color matching cost for image completion. We show that our system is capable of handling a variety of challenging examples.",
author = "Huang, {Jia Bin} and Johannes Kopf and Narendra Ahuja and Kang, {Sing Bing}",
year = "2013",
month = "8",
day = "8",
doi = "10.1109/ICCPhot.2013.6528313",
language = "English (US)",
isbn = "9781467364645",
series = "2013 IEEE International Conference on Computational Photography, ICCP 2013",
booktitle = "2013 IEEE International Conference on Computational Photography, ICCP 2013",

}

TY - GEN

T1 - Transformation guided image completion

AU - Huang, Jia Bin

AU - Kopf, Johannes

AU - Ahuja, Narendra

AU - Kang, Sing Bing

PY - 2013/8/8

Y1 - 2013/8/8

N2 - In this paper, we describe a new interactive image completion system that allows users to easily specify various forms of mid-level structures in the image. Our system supports the specification of four basic symmetric types: reflection, translation, rotation, and glide. The user inputs are automatically converted into guidance maps that encode possible candidate shifts and, indirectly, local transformations of rotation and scale. These guidance maps are used in conjunction with a color matching cost for image completion. We show that our system is capable of handling a variety of challenging examples.

AB - In this paper, we describe a new interactive image completion system that allows users to easily specify various forms of mid-level structures in the image. Our system supports the specification of four basic symmetric types: reflection, translation, rotation, and glide. The user inputs are automatically converted into guidance maps that encode possible candidate shifts and, indirectly, local transformations of rotation and scale. These guidance maps are used in conjunction with a color matching cost for image completion. We show that our system is capable of handling a variety of challenging examples.

UR - http://www.scopus.com/inward/record.url?scp=84881073820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881073820&partnerID=8YFLogxK

U2 - 10.1109/ICCPhot.2013.6528313

DO - 10.1109/ICCPhot.2013.6528313

M3 - Conference contribution

AN - SCOPUS:84881073820

SN - 9781467364645

T3 - 2013 IEEE International Conference on Computational Photography, ICCP 2013

BT - 2013 IEEE International Conference on Computational Photography, ICCP 2013

ER -