An object inpainting algorithm for multi-view video sequences

Soon Young Lee, Jun Hee Heu, Chang-Su Kim, Sang Uk Lee

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

4 Citations (Scopus)

Abstract

An inpainting algorithm for multi-view video sequences is proposed in this work. First, we set a mask region in a view with manual interactions, and find the corresponding masks in the other views using the mask cloning method. Then, we overlay grid points on the mask region in the target view frame. For each grid rectangle, we find the matching patch in the source view frame. Finally, we transform and paste the patches to the target frame. Simulation results illustrate that the proposed algorithm removes objects in the multi-view sequences effectively by exploiting inter-view redundancies.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages533-536
Number of pages4
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 IEEE International Conference on Image Processing, ICIP 2008 - San Diego, CA, United States
Duration: 2008 Oct 122008 Oct 15

Other

Other2008 IEEE International Conference on Image Processing, ICIP 2008
CountryUnited States
CitySan Diego, CA
Period08/10/1208/10/15

Fingerprint

Masks
Cloning
Redundancy

Keywords

  • Correspondence matching
  • Multi-view video
  • Object removal
  • Video inpainting

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Lee, S. Y., Heu, J. H., Kim, C-S., & Lee, S. U. (2008). An object inpainting algorithm for multi-view video sequences. In Proceedings - International Conference on Image Processing, ICIP (pp. 533-536). [4711809] https://doi.org/10.1109/ICIP.2008.4711809

An object inpainting algorithm for multi-view video sequences. / Lee, Soon Young; Heu, Jun Hee; Kim, Chang-Su; Lee, Sang Uk.

Proceedings - International Conference on Image Processing, ICIP. 2008. p. 533-536 4711809.

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

Lee, SY, Heu, JH, Kim, C-S & Lee, SU 2008, An object inpainting algorithm for multi-view video sequences. in Proceedings - International Conference on Image Processing, ICIP., 4711809, pp. 533-536, 2008 IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, United States, 08/10/12. https://doi.org/10.1109/ICIP.2008.4711809
Lee SY, Heu JH, Kim C-S, Lee SU. An object inpainting algorithm for multi-view video sequences. In Proceedings - International Conference on Image Processing, ICIP. 2008. p. 533-536. 4711809 https://doi.org/10.1109/ICIP.2008.4711809
Lee, Soon Young ; Heu, Jun Hee ; Kim, Chang-Su ; Lee, Sang Uk. / An object inpainting algorithm for multi-view video sequences. Proceedings - International Conference on Image Processing, ICIP. 2008. pp. 533-536
@inproceedings{072d2f255bdc43b2985fab64275fa42b,
title = "An object inpainting algorithm for multi-view video sequences",
abstract = "An inpainting algorithm for multi-view video sequences is proposed in this work. First, we set a mask region in a view with manual interactions, and find the corresponding masks in the other views using the mask cloning method. Then, we overlay grid points on the mask region in the target view frame. For each grid rectangle, we find the matching patch in the source view frame. Finally, we transform and paste the patches to the target frame. Simulation results illustrate that the proposed algorithm removes objects in the multi-view sequences effectively by exploiting inter-view redundancies.",
keywords = "Correspondence matching, Multi-view video, Object removal, Video inpainting",
author = "Lee, {Soon Young} and Heu, {Jun Hee} and Chang-Su Kim and Lee, {Sang Uk}",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/ICIP.2008.4711809",
language = "English",
isbn = "1424417643",
pages = "533--536",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - An object inpainting algorithm for multi-view video sequences

AU - Lee, Soon Young

AU - Heu, Jun Hee

AU - Kim, Chang-Su

AU - Lee, Sang Uk

PY - 2008/12/1

Y1 - 2008/12/1

N2 - An inpainting algorithm for multi-view video sequences is proposed in this work. First, we set a mask region in a view with manual interactions, and find the corresponding masks in the other views using the mask cloning method. Then, we overlay grid points on the mask region in the target view frame. For each grid rectangle, we find the matching patch in the source view frame. Finally, we transform and paste the patches to the target frame. Simulation results illustrate that the proposed algorithm removes objects in the multi-view sequences effectively by exploiting inter-view redundancies.

AB - An inpainting algorithm for multi-view video sequences is proposed in this work. First, we set a mask region in a view with manual interactions, and find the corresponding masks in the other views using the mask cloning method. Then, we overlay grid points on the mask region in the target view frame. For each grid rectangle, we find the matching patch in the source view frame. Finally, we transform and paste the patches to the target frame. Simulation results illustrate that the proposed algorithm removes objects in the multi-view sequences effectively by exploiting inter-view redundancies.

KW - Correspondence matching

KW - Multi-view video

KW - Object removal

KW - Video inpainting

UR - http://www.scopus.com/inward/record.url?scp=69949137324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69949137324&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2008.4711809

DO - 10.1109/ICIP.2008.4711809

M3 - Conference contribution

AN - SCOPUS:69949137324

SN - 1424417643

SN - 9781424417643

SP - 533

EP - 536

BT - Proceedings - International Conference on Image Processing, ICIP

ER -