Multiview image and video interpolation using weighted vector median filters

Guilherme P. Fickel; Claudio R. Jung; Bowon Lee

doi:10.1109/ICIP.2014.7026090

Multiview image and video interpolation using weighted vector median filters

Guilherme P. Fickel, Claudio R. Jung, Bowon Lee

Universidade Federal do Rio Grande do Sul

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

In Depth Image-Based Rendering (DIBR), interpolated views generated using one or two cameras usually present artifacts and holes due to occlusions and/or inconsistencies in the input disparity maps. In this paper we propose a multiple (3 or more) camera view interpolation technique that is able to combine redundant projections in a single interpolated view by using Weighted Vector Median Filters (WVMFs). By expressing the weights of the WVMF using both the distance from each reference view to the synthetic view and a measure of consonance of each projection to the others, we achieve a high quality view interpolation without holes and common visual artifacts, such as cracks and ghost effects. Additionally, we present an extension to multiview video sequences by imposing temporal coherence in the estimated disparity maps.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5387-5391
Number of pages	5
ISBN (Electronic)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7026090
State	Published - 28 Jan 2014

Publication series

Name	2014 IEEE International Conference on Image Processing, ICIP 2014

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

Multiview
disparity estimation
temporal coherence
view interpolation

Access to Document

10.1109/ICIP.2014.7026090

Cite this

Fickel, G. P., Jung, C. R., & Lee, B. (2014). Multiview image and video interpolation using weighted vector median filters. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 5387-5391). Article 7026090 (2014 IEEE International Conference on Image Processing, ICIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7026090

@inproceedings{6bd25f93d6fb4ca5987917acc9e24e5d,

title = "Multiview image and video interpolation using weighted vector median filters",

abstract = "In Depth Image-Based Rendering (DIBR), interpolated views generated using one or two cameras usually present artifacts and holes due to occlusions and/or inconsistencies in the input disparity maps. In this paper we propose a multiple (3 or more) camera view interpolation technique that is able to combine redundant projections in a single interpolated view by using Weighted Vector Median Filters (WVMFs). By expressing the weights of the WVMF using both the distance from each reference view to the synthetic view and a measure of consonance of each projection to the others, we achieve a high quality view interpolation without holes and common visual artifacts, such as cracks and ghost effects. Additionally, we present an extension to multiview video sequences by imposing temporal coherence in the estimated disparity maps.",

keywords = "Multiview, disparity estimation, temporal coherence, view interpolation",

author = "Fickel, {Guilherme P.} and Jung, {Claudio R.} and Bowon Lee",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7026090",

language = "English",

series = "2014 IEEE International Conference on Image Processing, ICIP 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5387--5391",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

address = "United States",

}

Fickel, GP, Jung, CR & Lee, B 2014, Multiview image and video interpolation using weighted vector median filters. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7026090, 2014 IEEE International Conference on Image Processing, ICIP 2014, Institute of Electrical and Electronics Engineers Inc., pp. 5387-5391. https://doi.org/10.1109/ICIP.2014.7026090

Multiview image and video interpolation using weighted vector median filters. / Fickel, Guilherme P.; Jung, Claudio R.; Lee, Bowon.
2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 5387-5391 7026090 (2014 IEEE International Conference on Image Processing, ICIP 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multiview image and video interpolation using weighted vector median filters

AU - Fickel, Guilherme P.

AU - Jung, Claudio R.

AU - Lee, Bowon

PY - 2014/1/28

Y1 - 2014/1/28

N2 - In Depth Image-Based Rendering (DIBR), interpolated views generated using one or two cameras usually present artifacts and holes due to occlusions and/or inconsistencies in the input disparity maps. In this paper we propose a multiple (3 or more) camera view interpolation technique that is able to combine redundant projections in a single interpolated view by using Weighted Vector Median Filters (WVMFs). By expressing the weights of the WVMF using both the distance from each reference view to the synthetic view and a measure of consonance of each projection to the others, we achieve a high quality view interpolation without holes and common visual artifacts, such as cracks and ghost effects. Additionally, we present an extension to multiview video sequences by imposing temporal coherence in the estimated disparity maps.

AB - In Depth Image-Based Rendering (DIBR), interpolated views generated using one or two cameras usually present artifacts and holes due to occlusions and/or inconsistencies in the input disparity maps. In this paper we propose a multiple (3 or more) camera view interpolation technique that is able to combine redundant projections in a single interpolated view by using Weighted Vector Median Filters (WVMFs). By expressing the weights of the WVMF using both the distance from each reference view to the synthetic view and a measure of consonance of each projection to the others, we achieve a high quality view interpolation without holes and common visual artifacts, such as cracks and ghost effects. Additionally, we present an extension to multiview video sequences by imposing temporal coherence in the estimated disparity maps.

KW - Multiview

KW - disparity estimation

KW - temporal coherence

KW - view interpolation

UR - http://www.scopus.com/inward/record.url?scp=84949928306&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7026090

DO - 10.1109/ICIP.2014.7026090

M3 - Conference contribution

AN - SCOPUS:84949928306

T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014

SP - 5387

EP - 5391

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Multiview image and video interpolation using weighted vector median filters

Abstract

Publication series

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this