Subjective and objective evaluation of image inpainting quality

Philipp Tiefenbacher; Viktor Bogischef; Daniel Merget; Gerhard Rigoll

doi:10.1109/ICIP.2015.7350838

Subjective and objective evaluation of image inpainting quality

Philipp Tiefenbacher, Viktor Bogischef, Daniel Merget, Gerhard Rigoll

Chair of Human-Machine Communication

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

24 Scopus citations

Abstract

Image inpainting algorithms aim to cut out parts of the image without leaving holes. Various algorithms exist, but no wider comparison has been made, yet. This work fills the gap by comparing state-of-the-art algorithms in a user study. We create and publish a database consisting of multiple base images and inpaint them using different inpainting concepts. Afterwards, 21 participants are asked to rate the quality of these inpainted images. The subjective feedback indicates that different image inpainting algorithms are favorable depending on the characteristics of the base image and target region. Furthermore, the results show that general image quality measures such as the peak signal-to-noise ratio (PSNR) or the structural similarity (SSIM) index are not suited for judging inpainting quality.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Publisher	IEEE Computer Society
Pages	447-451
Number of pages	5
ISBN (Electronic)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7350838
State	Published - 9 Dec 2015
Event	IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: 27 Sep 2015 → 30 Sep 2015

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2015-December
ISSN (Print)	1522-4880

Conference

Conference	IEEE International Conference on Image Processing, ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	27/09/15 → 30/09/15

Keywords

PSNR
SSIM
inpainting
quality
user study

Access to Document

10.1109/ICIP.2015.7350838

Cite this

Tiefenbacher, P., Bogischef, V., Merget, D., & Rigoll, G. (2015). Subjective and objective evaluation of image inpainting quality. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings (pp. 447-451). Article 7350838 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December). IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7350838

@inproceedings{467e829724e1461cae77ebc4b5d5675e,

title = "Subjective and objective evaluation of image inpainting quality",

abstract = "Image inpainting algorithms aim to cut out parts of the image without leaving holes. Various algorithms exist, but no wider comparison has been made, yet. This work fills the gap by comparing state-of-the-art algorithms in a user study. We create and publish a database consisting of multiple base images and inpaint them using different inpainting concepts. Afterwards, 21 participants are asked to rate the quality of these inpainted images. The subjective feedback indicates that different image inpainting algorithms are favorable depending on the characteristics of the base image and target region. Furthermore, the results show that general image quality measures such as the peak signal-to-noise ratio (PSNR) or the structural similarity (SSIM) index are not suited for judging inpainting quality.",

keywords = "PSNR, SSIM, inpainting, quality, user study",

author = "Philipp Tiefenbacher and Viktor Bogischef and Daniel Merget and Gerhard Rigoll",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Conference on Image Processing, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7350838",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "447--451",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

}

Tiefenbacher, P, Bogischef, V, Merget, D & Rigoll, G 2015, Subjective and objective evaluation of image inpainting quality. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings., 7350838, Proceedings - International Conference on Image Processing, ICIP, vol. 2015-December, IEEE Computer Society, pp. 447-451, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7350838

Subjective and objective evaluation of image inpainting quality. / Tiefenbacher, Philipp; Bogischef, Viktor; Merget, Daniel et al.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. IEEE Computer Society, 2015. p. 447-451 7350838 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Subjective and objective evaluation of image inpainting quality

AU - Tiefenbacher, Philipp

AU - Bogischef, Viktor

AU - Merget, Daniel

AU - Rigoll, Gerhard

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Image inpainting algorithms aim to cut out parts of the image without leaving holes. Various algorithms exist, but no wider comparison has been made, yet. This work fills the gap by comparing state-of-the-art algorithms in a user study. We create and publish a database consisting of multiple base images and inpaint them using different inpainting concepts. Afterwards, 21 participants are asked to rate the quality of these inpainted images. The subjective feedback indicates that different image inpainting algorithms are favorable depending on the characteristics of the base image and target region. Furthermore, the results show that general image quality measures such as the peak signal-to-noise ratio (PSNR) or the structural similarity (SSIM) index are not suited for judging inpainting quality.

AB - Image inpainting algorithms aim to cut out parts of the image without leaving holes. Various algorithms exist, but no wider comparison has been made, yet. This work fills the gap by comparing state-of-the-art algorithms in a user study. We create and publish a database consisting of multiple base images and inpaint them using different inpainting concepts. Afterwards, 21 participants are asked to rate the quality of these inpainted images. The subjective feedback indicates that different image inpainting algorithms are favorable depending on the characteristics of the base image and target region. Furthermore, the results show that general image quality measures such as the peak signal-to-noise ratio (PSNR) or the structural similarity (SSIM) index are not suited for judging inpainting quality.

KW - PSNR

KW - SSIM

KW - inpainting

KW - quality

KW - user study

UR - http://www.scopus.com/inward/record.url?scp=84956698201&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7350838

DO - 10.1109/ICIP.2015.7350838

M3 - Conference contribution

AN - SCOPUS:84956698201

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 447

EP - 451

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE Computer Society

T2 - IEEE International Conference on Image Processing, ICIP 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Subjective and objective evaluation of image inpainting quality

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this