Scalable and Coherent Video Resizing with Per-Frame Optimization

Yu Shuen Wang, Yu Shuen Wang, Jen Hung Hsiao, Tong-Yee Lee, Olga Sorkine, Olga Sorkine

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The key to high-quality video resizing is preserving the shape and motion of visually salient objects while remaining temporallycoherent. These spatial and temporal requirements are difficult to reconcile, typically leading existing video retargeting methods to sacrifice one of them and causing distortion or waving artifacts. Recent work enforces temporal coherence of content-aware video warping by solving a global optimization problem over the entire video cube. This significantly improves the results but does not scale well with the resolution and length of the input video and quickly becomes intractable. We propose a new method that solves the scalability problem without compromising the resizing quality. Our method factors the problem into spatial and time/motion components: we first resize each frame independently to preserve the shape of salient regions, and then we optimize their motion using a reduced model for each pathline of the optical flow. This factorization decomposes the optimization of the video cube into sets of subproblems whose size is proportional to a single frame's resolution and which can be solved in parallel. We also show how to incorporate cropping into our optimization, which is useful for scenes with numerous salient objects where warping alone would degenerate to linear scaling. Our results match the quality of state-of-the-art retargeting methods while dramatically reducing the computation time and memory consumption, making content-aware video resizing scalable and practical.

Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalACM Transactions on Graphics
Volume30
Issue number4
DOIs
Publication statusPublished - 2011 Jul 1

Fingerprint

Optical flows
Global optimization
Factorization
Scalability
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Cite this

Wang, Yu Shuen ; Wang, Yu Shuen ; Hsiao, Jen Hung ; Lee, Tong-Yee ; Sorkine, Olga ; Sorkine, Olga. / Scalable and Coherent Video Resizing with Per-Frame Optimization. In: ACM Transactions on Graphics. 2011 ; Vol. 30, No. 4. pp. 1-8.
@article{2ecc374030cc45898f8dc0c211931c67,
title = "Scalable and Coherent Video Resizing with Per-Frame Optimization",
abstract = "The key to high-quality video resizing is preserving the shape and motion of visually salient objects while remaining temporallycoherent. These spatial and temporal requirements are difficult to reconcile, typically leading existing video retargeting methods to sacrifice one of them and causing distortion or waving artifacts. Recent work enforces temporal coherence of content-aware video warping by solving a global optimization problem over the entire video cube. This significantly improves the results but does not scale well with the resolution and length of the input video and quickly becomes intractable. We propose a new method that solves the scalability problem without compromising the resizing quality. Our method factors the problem into spatial and time/motion components: we first resize each frame independently to preserve the shape of salient regions, and then we optimize their motion using a reduced model for each pathline of the optical flow. This factorization decomposes the optimization of the video cube into sets of subproblems whose size is proportional to a single frame's resolution and which can be solved in parallel. We also show how to incorporate cropping into our optimization, which is useful for scenes with numerous salient objects where warping alone would degenerate to linear scaling. Our results match the quality of state-of-the-art retargeting methods while dramatically reducing the computation time and memory consumption, making content-aware video resizing scalable and practical.",
author = "Wang, {Yu Shuen} and Wang, {Yu Shuen} and Hsiao, {Jen Hung} and Tong-Yee Lee and Olga Sorkine and Olga Sorkine",
year = "2011",
month = "7",
day = "1",
doi = "10.1145/2010324.1964983",
language = "English",
volume = "30",
pages = "1--8",
journal = "ACM Transactions on Graphics",
issn = "0730-0301",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

Scalable and Coherent Video Resizing with Per-Frame Optimization. / Wang, Yu Shuen; Wang, Yu Shuen; Hsiao, Jen Hung; Lee, Tong-Yee; Sorkine, Olga; Sorkine, Olga.

In: ACM Transactions on Graphics, Vol. 30, No. 4, 01.07.2011, p. 1-8.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Scalable and Coherent Video Resizing with Per-Frame Optimization

AU - Wang, Yu Shuen

AU - Wang, Yu Shuen

AU - Hsiao, Jen Hung

AU - Lee, Tong-Yee

AU - Sorkine, Olga

AU - Sorkine, Olga

PY - 2011/7/1

Y1 - 2011/7/1

N2 - The key to high-quality video resizing is preserving the shape and motion of visually salient objects while remaining temporallycoherent. These spatial and temporal requirements are difficult to reconcile, typically leading existing video retargeting methods to sacrifice one of them and causing distortion or waving artifacts. Recent work enforces temporal coherence of content-aware video warping by solving a global optimization problem over the entire video cube. This significantly improves the results but does not scale well with the resolution and length of the input video and quickly becomes intractable. We propose a new method that solves the scalability problem without compromising the resizing quality. Our method factors the problem into spatial and time/motion components: we first resize each frame independently to preserve the shape of salient regions, and then we optimize their motion using a reduced model for each pathline of the optical flow. This factorization decomposes the optimization of the video cube into sets of subproblems whose size is proportional to a single frame's resolution and which can be solved in parallel. We also show how to incorporate cropping into our optimization, which is useful for scenes with numerous salient objects where warping alone would degenerate to linear scaling. Our results match the quality of state-of-the-art retargeting methods while dramatically reducing the computation time and memory consumption, making content-aware video resizing scalable and practical.

AB - The key to high-quality video resizing is preserving the shape and motion of visually salient objects while remaining temporallycoherent. These spatial and temporal requirements are difficult to reconcile, typically leading existing video retargeting methods to sacrifice one of them and causing distortion or waving artifacts. Recent work enforces temporal coherence of content-aware video warping by solving a global optimization problem over the entire video cube. This significantly improves the results but does not scale well with the resolution and length of the input video and quickly becomes intractable. We propose a new method that solves the scalability problem without compromising the resizing quality. Our method factors the problem into spatial and time/motion components: we first resize each frame independently to preserve the shape of salient regions, and then we optimize their motion using a reduced model for each pathline of the optical flow. This factorization decomposes the optimization of the video cube into sets of subproblems whose size is proportional to a single frame's resolution and which can be solved in parallel. We also show how to incorporate cropping into our optimization, which is useful for scenes with numerous salient objects where warping alone would degenerate to linear scaling. Our results match the quality of state-of-the-art retargeting methods while dramatically reducing the computation time and memory consumption, making content-aware video resizing scalable and practical.

UR - http://www.scopus.com/inward/record.url?scp=84884833528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884833528&partnerID=8YFLogxK

U2 - 10.1145/2010324.1964983

DO - 10.1145/2010324.1964983

M3 - Article

AN - SCOPUS:84884833528

VL - 30

SP - 1

EP - 8

JO - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

SN - 0730-0301

IS - 4

ER -