Motion-aware temporal coherence for video resizing

Yu Shuen Wang, Hongbo Fu, Olga Sorkine, Tong-Yee Lee, Hans Peter Seidel

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

101 Citations (Scopus)

Abstract

Temporal coherence is crucial in content-aware video retargeting. To date, this problem has been addressed by constraining temporally adjacent pixels to be transformed coherently. However, due to the motion-oblivious nature of this simple constraint, the retargeted videos often exhibit flickering or waving artifacts, especially when significant camera or object motions are involved. Since the feature correspondence across frames varies spatially with both camera and object motion, motion-aware treatment of features is required for video resizing. This motivated us to align consecutive frames by estimating interframe camera motion and to constrain relative positions in the aligned frames. To preserve object motion, we detect distinct moving areas of objects across multiple frames and constrain each of them to be resized consistently. We build a complete video resizing framework by incorporating our motion-aware constraints with an adaptation of the scale-and-stretch optimization recently proposed by Wang and colleagues. Our streaming implementation of the framework allows efficient resizing of long video sequences with low memory cost. Experiments demonstrate that our method produces spatiotemporally coherent retargeting results even for challenging examples with complex camera and object motion, which are difficult to handle with previous techniques.

Original languageEnglish
Title of host publicationProceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09
Volume28
Edition5
DOIs
Publication statusPublished - 2009 Dec 1
EventACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09 - Yokohama, Japan
Duration: 2009 Dec 162009 Dec 19

Other

OtherACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09
CountryJapan
CityYokohama
Period09-12-1609-12-19

Fingerprint

Cameras
Flickering
Pixels
Data storage equipment
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Cite this

Wang, Y. S., Fu, H., Sorkine, O., Lee, T-Y., & Seidel, H. P. (2009). Motion-aware temporal coherence for video resizing. In Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09 (5 ed., Vol. 28) https://doi.org/10.1145/1661412.1618473
Wang, Yu Shuen ; Fu, Hongbo ; Sorkine, Olga ; Lee, Tong-Yee ; Seidel, Hans Peter. / Motion-aware temporal coherence for video resizing. Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. Vol. 28 5. ed. 2009.
@inproceedings{544dfdb138f542049c8a0a832773ce66,
title = "Motion-aware temporal coherence for video resizing",
abstract = "Temporal coherence is crucial in content-aware video retargeting. To date, this problem has been addressed by constraining temporally adjacent pixels to be transformed coherently. However, due to the motion-oblivious nature of this simple constraint, the retargeted videos often exhibit flickering or waving artifacts, especially when significant camera or object motions are involved. Since the feature correspondence across frames varies spatially with both camera and object motion, motion-aware treatment of features is required for video resizing. This motivated us to align consecutive frames by estimating interframe camera motion and to constrain relative positions in the aligned frames. To preserve object motion, we detect distinct moving areas of objects across multiple frames and constrain each of them to be resized consistently. We build a complete video resizing framework by incorporating our motion-aware constraints with an adaptation of the scale-and-stretch optimization recently proposed by Wang and colleagues. Our streaming implementation of the framework allows efficient resizing of long video sequences with low memory cost. Experiments demonstrate that our method produces spatiotemporally coherent retargeting results even for challenging examples with complex camera and object motion, which are difficult to handle with previous techniques.",
author = "Wang, {Yu Shuen} and Hongbo Fu and Olga Sorkine and Tong-Yee Lee and Seidel, {Hans Peter}",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1661412.1618473",
language = "English",
isbn = "9781605588582",
volume = "28",
booktitle = "Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09",
edition = "5",

}

Wang, YS, Fu, H, Sorkine, O, Lee, T-Y & Seidel, HP 2009, Motion-aware temporal coherence for video resizing. in Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. 5 edn, vol. 28, ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09, Yokohama, Japan, 09-12-16. https://doi.org/10.1145/1661412.1618473

Motion-aware temporal coherence for video resizing. / Wang, Yu Shuen; Fu, Hongbo; Sorkine, Olga; Lee, Tong-Yee; Seidel, Hans Peter.

Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. Vol. 28 5. ed. 2009.

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

TY - GEN

T1 - Motion-aware temporal coherence for video resizing

AU - Wang, Yu Shuen

AU - Fu, Hongbo

AU - Sorkine, Olga

AU - Lee, Tong-Yee

AU - Seidel, Hans Peter

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Temporal coherence is crucial in content-aware video retargeting. To date, this problem has been addressed by constraining temporally adjacent pixels to be transformed coherently. However, due to the motion-oblivious nature of this simple constraint, the retargeted videos often exhibit flickering or waving artifacts, especially when significant camera or object motions are involved. Since the feature correspondence across frames varies spatially with both camera and object motion, motion-aware treatment of features is required for video resizing. This motivated us to align consecutive frames by estimating interframe camera motion and to constrain relative positions in the aligned frames. To preserve object motion, we detect distinct moving areas of objects across multiple frames and constrain each of them to be resized consistently. We build a complete video resizing framework by incorporating our motion-aware constraints with an adaptation of the scale-and-stretch optimization recently proposed by Wang and colleagues. Our streaming implementation of the framework allows efficient resizing of long video sequences with low memory cost. Experiments demonstrate that our method produces spatiotemporally coherent retargeting results even for challenging examples with complex camera and object motion, which are difficult to handle with previous techniques.

AB - Temporal coherence is crucial in content-aware video retargeting. To date, this problem has been addressed by constraining temporally adjacent pixels to be transformed coherently. However, due to the motion-oblivious nature of this simple constraint, the retargeted videos often exhibit flickering or waving artifacts, especially when significant camera or object motions are involved. Since the feature correspondence across frames varies spatially with both camera and object motion, motion-aware treatment of features is required for video resizing. This motivated us to align consecutive frames by estimating interframe camera motion and to constrain relative positions in the aligned frames. To preserve object motion, we detect distinct moving areas of objects across multiple frames and constrain each of them to be resized consistently. We build a complete video resizing framework by incorporating our motion-aware constraints with an adaptation of the scale-and-stretch optimization recently proposed by Wang and colleagues. Our streaming implementation of the framework allows efficient resizing of long video sequences with low memory cost. Experiments demonstrate that our method produces spatiotemporally coherent retargeting results even for challenging examples with complex camera and object motion, which are difficult to handle with previous techniques.

UR - http://www.scopus.com/inward/record.url?scp=77749264947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77749264947&partnerID=8YFLogxK

U2 - 10.1145/1661412.1618473

DO - 10.1145/1661412.1618473

M3 - Conference contribution

AN - SCOPUS:77749264947

SN - 9781605588582

VL - 28

BT - Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09

ER -

Wang YS, Fu H, Sorkine O, Lee T-Y, Seidel HP. Motion-aware temporal coherence for video resizing. In Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. 5 ed. Vol. 28. 2009 https://doi.org/10.1145/1661412.1618473