Object-coherence warping for stereoscopic image retargeting

Shih Syun Lin, Chao Hung Lin, Shu Huai Chang, Tong Yee Lee

研究成果: Article

26 引文 (Scopus)

摘要

This paper addresses the topic of content-aware stereoscopic image retargeting. The key to this topic is consistently adapting a stereoscopic image to fit displays with various aspect ratios and sizes while preserving visually salient content. Most methods focus on preserving the disparities and shapes of visually salient objects through nonlinear image warping, in which distortions caused by warping are propagated to homogenous and low-significance regions. However, disregarding the consistency of object deformation sometimes results in apparent distortions in both the disparities and shapes of objects. An object-coherence warping scheme is proposed to reduce this unwanted distortion. The basic idea is to utilize the information of matched objects rather than that of matched pixels in warping. Such information implies object correspondences in a stereoscopic image pair, which allows the generation of an object significance map and the consistent preservation of objects. This strategy enables our method to consistently preserve both the disparities and shapes of visually salient objects, leading to good content-aware retargeting. In the experiments, qualitative and quantitative analyses of various stereoscopic images show that our results are better than those generated by related methods in terms of consistency of object preservation.

原文English
文章編號6665052
頁(從 - 到)759-768
頁數10
期刊IEEE Transactions on Circuits and Systems for Video Technology
24
發行號5
DOIs
出版狀態Published - 2014 五月

指紋

Aspect ratio
Pixels
Display devices
Experiments

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

引用此文

@article{39aac9382bdd485d8cec6abdb6a5733f,
title = "Object-coherence warping for stereoscopic image retargeting",
abstract = "This paper addresses the topic of content-aware stereoscopic image retargeting. The key to this topic is consistently adapting a stereoscopic image to fit displays with various aspect ratios and sizes while preserving visually salient content. Most methods focus on preserving the disparities and shapes of visually salient objects through nonlinear image warping, in which distortions caused by warping are propagated to homogenous and low-significance regions. However, disregarding the consistency of object deformation sometimes results in apparent distortions in both the disparities and shapes of objects. An object-coherence warping scheme is proposed to reduce this unwanted distortion. The basic idea is to utilize the information of matched objects rather than that of matched pixels in warping. Such information implies object correspondences in a stereoscopic image pair, which allows the generation of an object significance map and the consistent preservation of objects. This strategy enables our method to consistently preserve both the disparities and shapes of visually salient objects, leading to good content-aware retargeting. In the experiments, qualitative and quantitative analyses of various stereoscopic images show that our results are better than those generated by related methods in terms of consistency of object preservation.",
author = "Lin, {Shih Syun} and Lin, {Chao Hung} and Chang, {Shu Huai} and Lee, {Tong Yee}",
year = "2014",
month = "5",
doi = "10.1109/TCSVT.2013.2291282",
language = "English",
volume = "24",
pages = "759--768",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

Object-coherence warping for stereoscopic image retargeting. / Lin, Shih Syun; Lin, Chao Hung; Chang, Shu Huai; Lee, Tong Yee.

於: IEEE Transactions on Circuits and Systems for Video Technology, 卷 24, 編號 5, 6665052, 05.2014, p. 759-768.

研究成果: Article

TY - JOUR

T1 - Object-coherence warping for stereoscopic image retargeting

AU - Lin, Shih Syun

AU - Lin, Chao Hung

AU - Chang, Shu Huai

AU - Lee, Tong Yee

PY - 2014/5

Y1 - 2014/5

N2 - This paper addresses the topic of content-aware stereoscopic image retargeting. The key to this topic is consistently adapting a stereoscopic image to fit displays with various aspect ratios and sizes while preserving visually salient content. Most methods focus on preserving the disparities and shapes of visually salient objects through nonlinear image warping, in which distortions caused by warping are propagated to homogenous and low-significance regions. However, disregarding the consistency of object deformation sometimes results in apparent distortions in both the disparities and shapes of objects. An object-coherence warping scheme is proposed to reduce this unwanted distortion. The basic idea is to utilize the information of matched objects rather than that of matched pixels in warping. Such information implies object correspondences in a stereoscopic image pair, which allows the generation of an object significance map and the consistent preservation of objects. This strategy enables our method to consistently preserve both the disparities and shapes of visually salient objects, leading to good content-aware retargeting. In the experiments, qualitative and quantitative analyses of various stereoscopic images show that our results are better than those generated by related methods in terms of consistency of object preservation.

AB - This paper addresses the topic of content-aware stereoscopic image retargeting. The key to this topic is consistently adapting a stereoscopic image to fit displays with various aspect ratios and sizes while preserving visually salient content. Most methods focus on preserving the disparities and shapes of visually salient objects through nonlinear image warping, in which distortions caused by warping are propagated to homogenous and low-significance regions. However, disregarding the consistency of object deformation sometimes results in apparent distortions in both the disparities and shapes of objects. An object-coherence warping scheme is proposed to reduce this unwanted distortion. The basic idea is to utilize the information of matched objects rather than that of matched pixels in warping. Such information implies object correspondences in a stereoscopic image pair, which allows the generation of an object significance map and the consistent preservation of objects. This strategy enables our method to consistently preserve both the disparities and shapes of visually salient objects, leading to good content-aware retargeting. In the experiments, qualitative and quantitative analyses of various stereoscopic images show that our results are better than those generated by related methods in terms of consistency of object preservation.

UR - http://www.scopus.com/inward/record.url?scp=84900542719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900542719&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2013.2291282

DO - 10.1109/TCSVT.2013.2291282

M3 - Article

AN - SCOPUS:84900542719

VL - 24

SP - 759

EP - 768

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 5

M1 - 6665052

ER -