Perception-motivated interpolation of image sequences

Timo Stich, Christian Linz, Christian Wallraven, Douglas Cunningham, Marcus Magnor

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

We present a method for image interpolation that is able to create high-quality, perceptually convincing transitions between recorded images. By implementing concepts derived from human vision, the problem of a physically correct image interpolation is relaxed to that of image interpolation which is perceived as visually correct by human observers. We find that it suffices to focus on exact edge correspondences, homogeneous regions and coherent motion to compute convincing results. A user study confirms the visual quality of the proposed image interpolation approach. We show how each aspect of our approach increases perceived quality of the result. We compare the results to other methods and assess achievable quality for different types of scenes.

Original languageEnglish
Article number11
JournalACM Transactions on Applied Perception
Volume8
Issue number2
DOIs
Publication statusPublished - 2011 Jan 1
Externally publishedYes

Fingerprint

Image Interpolation
Image Sequence
Interpolation
Interpolate
Human Vision
User Studies
Observer
Correspondence
Motion
Perception

Keywords

  • Image interpolation
  • Morphing
  • Perception

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science
  • Experimental and Cognitive Psychology

Cite this

Perception-motivated interpolation of image sequences. / Stich, Timo; Linz, Christian; Wallraven, Christian; Cunningham, Douglas; Magnor, Marcus.

In: ACM Transactions on Applied Perception, Vol. 8, No. 2, 11, 01.01.2011.

Research output: Contribution to journalArticle

Stich, Timo ; Linz, Christian ; Wallraven, Christian ; Cunningham, Douglas ; Magnor, Marcus. / Perception-motivated interpolation of image sequences. In: ACM Transactions on Applied Perception. 2011 ; Vol. 8, No. 2.
@article{8ce9de473b004263a476dfd660c4c2eb,
title = "Perception-motivated interpolation of image sequences",
abstract = "We present a method for image interpolation that is able to create high-quality, perceptually convincing transitions between recorded images. By implementing concepts derived from human vision, the problem of a physically correct image interpolation is relaxed to that of image interpolation which is perceived as visually correct by human observers. We find that it suffices to focus on exact edge correspondences, homogeneous regions and coherent motion to compute convincing results. A user study confirms the visual quality of the proposed image interpolation approach. We show how each aspect of our approach increases perceived quality of the result. We compare the results to other methods and assess achievable quality for different types of scenes.",
keywords = "Image interpolation, Morphing, Perception",
author = "Timo Stich and Christian Linz and Christian Wallraven and Douglas Cunningham and Marcus Magnor",
year = "2011",
month = "1",
day = "1",
doi = "10.1145/1870076.1870079",
language = "English",
volume = "8",
journal = "ACM Transactions on Applied Perception",
issn = "1544-3558",
publisher = "Association for Computing Machinery (ACM)",
number = "2",

}

TY - JOUR

T1 - Perception-motivated interpolation of image sequences

AU - Stich, Timo

AU - Linz, Christian

AU - Wallraven, Christian

AU - Cunningham, Douglas

AU - Magnor, Marcus

PY - 2011/1/1

Y1 - 2011/1/1

N2 - We present a method for image interpolation that is able to create high-quality, perceptually convincing transitions between recorded images. By implementing concepts derived from human vision, the problem of a physically correct image interpolation is relaxed to that of image interpolation which is perceived as visually correct by human observers. We find that it suffices to focus on exact edge correspondences, homogeneous regions and coherent motion to compute convincing results. A user study confirms the visual quality of the proposed image interpolation approach. We show how each aspect of our approach increases perceived quality of the result. We compare the results to other methods and assess achievable quality for different types of scenes.

AB - We present a method for image interpolation that is able to create high-quality, perceptually convincing transitions between recorded images. By implementing concepts derived from human vision, the problem of a physically correct image interpolation is relaxed to that of image interpolation which is perceived as visually correct by human observers. We find that it suffices to focus on exact edge correspondences, homogeneous regions and coherent motion to compute convincing results. A user study confirms the visual quality of the proposed image interpolation approach. We show how each aspect of our approach increases perceived quality of the result. We compare the results to other methods and assess achievable quality for different types of scenes.

KW - Image interpolation

KW - Morphing

KW - Perception

UR - http://www.scopus.com/inward/record.url?scp=79551714517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79551714517&partnerID=8YFLogxK

U2 - 10.1145/1870076.1870079

DO - 10.1145/1870076.1870079

M3 - Article

AN - SCOPUS:79551714517

VL - 8

JO - ACM Transactions on Applied Perception

JF - ACM Transactions on Applied Perception

SN - 1544-3558

IS - 2

M1 - 11

ER -