Object removal and inpainting in multi-view video sequences

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

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

An inpainting algorithm for multi-view video sequences, which fills in a mask area without visual artifacts, is proposed in this work. After a user specifies a mask area in a frame, the proposed algorithm clones it to the other frames in the input sequence using temporal and inter-view correlations. The proposed algorithm then selects sites along the mask boundary, over which source blocks are pasted. We develop a cost function, which measures the spatio-temporal consistency of an inpainted result, and minimize the cost function to select the best matching source blocks. Simulation results demonstrate that the proposed algorithm removes and inpaints objects within mask areas efficiently without causing blocking or flickering artifacts.

Original languageEnglish
Pages (from-to)1241-1255
Number of pages15
JournalInternational Journal of Innovative Computing, Information and Control
Volume6
Issue number3
Publication statusPublished - 2010 Mar 1

Fingerprint

Inpainting
Mask
Masks
Cost functions
Cost Function
Flickering
Clone
Minimise
Object
Demonstrate
Simulation

Keywords

  • Image inpainting
  • Multi-view video
  • Object removal
  • Video editing

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Software
  • Theoretical Computer Science

Cite this

Object removal and inpainting in multi-view video sequences. / Lee, Soon Young; Heu, Jun Hee; Kim, Chang-Su; Lee, Sang Uk.

In: International Journal of Innovative Computing, Information and Control, Vol. 6, No. 3, 01.03.2010, p. 1241-1255.

Research output: Contribution to journalArticle

@article{f5568b521e964518b776a2cffa4e733f,
title = "Object removal and inpainting in multi-view video sequences",
abstract = "An inpainting algorithm for multi-view video sequences, which fills in a mask area without visual artifacts, is proposed in this work. After a user specifies a mask area in a frame, the proposed algorithm clones it to the other frames in the input sequence using temporal and inter-view correlations. The proposed algorithm then selects sites along the mask boundary, over which source blocks are pasted. We develop a cost function, which measures the spatio-temporal consistency of an inpainted result, and minimize the cost function to select the best matching source blocks. Simulation results demonstrate that the proposed algorithm removes and inpaints objects within mask areas efficiently without causing blocking or flickering artifacts.",
keywords = "Image inpainting, Multi-view video, Object removal, Video editing",
author = "Lee, {Soon Young} and Heu, {Jun Hee} and Chang-Su Kim and Lee, {Sang Uk}",
year = "2010",
month = "3",
day = "1",
language = "English",
volume = "6",
pages = "1241--1255",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "3",

}

TY - JOUR

T1 - Object removal and inpainting in multi-view video sequences

AU - Lee, Soon Young

AU - Heu, Jun Hee

AU - Kim, Chang-Su

AU - Lee, Sang Uk

PY - 2010/3/1

Y1 - 2010/3/1

N2 - An inpainting algorithm for multi-view video sequences, which fills in a mask area without visual artifacts, is proposed in this work. After a user specifies a mask area in a frame, the proposed algorithm clones it to the other frames in the input sequence using temporal and inter-view correlations. The proposed algorithm then selects sites along the mask boundary, over which source blocks are pasted. We develop a cost function, which measures the spatio-temporal consistency of an inpainted result, and minimize the cost function to select the best matching source blocks. Simulation results demonstrate that the proposed algorithm removes and inpaints objects within mask areas efficiently without causing blocking or flickering artifacts.

AB - An inpainting algorithm for multi-view video sequences, which fills in a mask area without visual artifacts, is proposed in this work. After a user specifies a mask area in a frame, the proposed algorithm clones it to the other frames in the input sequence using temporal and inter-view correlations. The proposed algorithm then selects sites along the mask boundary, over which source blocks are pasted. We develop a cost function, which measures the spatio-temporal consistency of an inpainted result, and minimize the cost function to select the best matching source blocks. Simulation results demonstrate that the proposed algorithm removes and inpaints objects within mask areas efficiently without causing blocking or flickering artifacts.

KW - Image inpainting

KW - Multi-view video

KW - Object removal

KW - Video editing

UR - http://www.scopus.com/inward/record.url?scp=77950132934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950132934&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:77950132934

VL - 6

SP - 1241

EP - 1255

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 3

ER -