Exemplar-based frame rate up-conversion with congruent segmentation

Seong Gyun Jeong, Chul Lee, Chang-Su Kim

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

2 Citations (Scopus)

Abstract

A novel motion-compensated frame interpolation algorithm to increase video frame rates is proposed in this work, which employs texture optimization techniques to refine inaccurate motion vector fields. We enforce the congruent segment constraint in the motion refinement so that matching objects have similar local image structures. More specifically, we use the congruence energy as well as the appearance energy in the motion optimization to estimate high quality motion vectors. Simulation results show that, by preserving complex object shapes and texture, the proposed algorithm provides more faithful intermediate frames than conventional algorithms.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages845-848
Number of pages4
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, United States
Duration: 2012 Sep 302012 Oct 3

Other

Other2012 19th IEEE International Conference on Image Processing, ICIP 2012
CountryUnited States
CityLake Buena Vista, FL
Period12/9/3012/10/3

Fingerprint

Textures
Interpolation

Keywords

  • exemplar-based texture synthesis
  • Frame rate up-conversion
  • motion-compensated frame interpolation
  • video segmentation

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Jeong, S. G., Lee, C., & Kim, C-S. (2012). Exemplar-based frame rate up-conversion with congruent segmentation. In Proceedings - International Conference on Image Processing, ICIP (pp. 845-848). [6466992] https://doi.org/10.1109/ICIP.2012.6466992

Exemplar-based frame rate up-conversion with congruent segmentation. / Jeong, Seong Gyun; Lee, Chul; Kim, Chang-Su.

Proceedings - International Conference on Image Processing, ICIP. 2012. p. 845-848 6466992.

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

Jeong, SG, Lee, C & Kim, C-S 2012, Exemplar-based frame rate up-conversion with congruent segmentation. in Proceedings - International Conference on Image Processing, ICIP., 6466992, pp. 845-848, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, United States, 12/9/30. https://doi.org/10.1109/ICIP.2012.6466992
Jeong SG, Lee C, Kim C-S. Exemplar-based frame rate up-conversion with congruent segmentation. In Proceedings - International Conference on Image Processing, ICIP. 2012. p. 845-848. 6466992 https://doi.org/10.1109/ICIP.2012.6466992
Jeong, Seong Gyun ; Lee, Chul ; Kim, Chang-Su. / Exemplar-based frame rate up-conversion with congruent segmentation. Proceedings - International Conference on Image Processing, ICIP. 2012. pp. 845-848
@inproceedings{a096bdb6090c478f850e98662b715d7f,
title = "Exemplar-based frame rate up-conversion with congruent segmentation",
abstract = "A novel motion-compensated frame interpolation algorithm to increase video frame rates is proposed in this work, which employs texture optimization techniques to refine inaccurate motion vector fields. We enforce the congruent segment constraint in the motion refinement so that matching objects have similar local image structures. More specifically, we use the congruence energy as well as the appearance energy in the motion optimization to estimate high quality motion vectors. Simulation results show that, by preserving complex object shapes and texture, the proposed algorithm provides more faithful intermediate frames than conventional algorithms.",
keywords = "exemplar-based texture synthesis, Frame rate up-conversion, motion-compensated frame interpolation, video segmentation",
author = "Jeong, {Seong Gyun} and Chul Lee and Chang-Su Kim",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICIP.2012.6466992",
language = "English",
isbn = "9781467325332",
pages = "845--848",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Exemplar-based frame rate up-conversion with congruent segmentation

AU - Jeong, Seong Gyun

AU - Lee, Chul

AU - Kim, Chang-Su

PY - 2012/12/1

Y1 - 2012/12/1

N2 - A novel motion-compensated frame interpolation algorithm to increase video frame rates is proposed in this work, which employs texture optimization techniques to refine inaccurate motion vector fields. We enforce the congruent segment constraint in the motion refinement so that matching objects have similar local image structures. More specifically, we use the congruence energy as well as the appearance energy in the motion optimization to estimate high quality motion vectors. Simulation results show that, by preserving complex object shapes and texture, the proposed algorithm provides more faithful intermediate frames than conventional algorithms.

AB - A novel motion-compensated frame interpolation algorithm to increase video frame rates is proposed in this work, which employs texture optimization techniques to refine inaccurate motion vector fields. We enforce the congruent segment constraint in the motion refinement so that matching objects have similar local image structures. More specifically, we use the congruence energy as well as the appearance energy in the motion optimization to estimate high quality motion vectors. Simulation results show that, by preserving complex object shapes and texture, the proposed algorithm provides more faithful intermediate frames than conventional algorithms.

KW - exemplar-based texture synthesis

KW - Frame rate up-conversion

KW - motion-compensated frame interpolation

KW - video segmentation

UR - http://www.scopus.com/inward/record.url?scp=84875872447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875872447&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6466992

DO - 10.1109/ICIP.2012.6466992

M3 - Conference contribution

SN - 9781467325332

SP - 845

EP - 848

BT - Proceedings - International Conference on Image Processing, ICIP

ER -