Multi-view Image Restoration From Plenoptic Raw Images

Nicholas Devaney

Multi-view Image Restoration From Plenoptic Raw Images

Nicholas Devaney

Physics

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

We present a reconstruction algorithm that can restore the captured 4D light field from a portable plenoptic camera without the need for calibration images. An efficient and robust estimator is proposed to accurately detect the centers of microlens images. Based on that estimator, parameters that model the centers of microlens array images are obtained by solving a global optimization problem. To further enhance the quality of reconstructed multi-view images, a novel 4D demosaicing algorithm based on kernel regression is also proposed. Our experimental results show that it outperforms the state of art algorithms.

Original language	English (Ireland)
Title of host publication	Asian Conference on Computer Vision 2014
Place of Publication	Singapore
Publication status	Published - 1 Jan 2015

Authors (Note for portal: view the doc link for the full list of authors)

Authors
Xu. S., Zhi-Liang, Z., Devaney, N.

Cite this

@inproceedings{1c0d2f0b5a634f54bef35d8e7d6c3823,

title = "Multi-view Image Restoration From Plenoptic Raw Images",

abstract = "We present a reconstruction algorithm that can restore the captured 4D light field from a portable plenoptic camera without the need for calibration images. An efficient and robust estimator is proposed to accurately detect the centers of microlens images. Based on that estimator, parameters that model the centers of microlens array images are obtained by solving a global optimization problem. To further enhance the quality of reconstructed multi-view images, a novel 4D demosaicing algorithm based on kernel regression is also proposed. Our experimental results show that it outperforms the state of art algorithms. ",

author = "Nicholas Devaney",

year = "2015",

month = jan,

day = "1",

language = "English (Ireland)",

booktitle = "Asian Conference on Computer Vision 2014",

}

TY - GEN

T1 - Multi-view Image Restoration From Plenoptic Raw Images

AU - Devaney, Nicholas

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We present a reconstruction algorithm that can restore the captured 4D light field from a portable plenoptic camera without the need for calibration images. An efficient and robust estimator is proposed to accurately detect the centers of microlens images. Based on that estimator, parameters that model the centers of microlens array images are obtained by solving a global optimization problem. To further enhance the quality of reconstructed multi-view images, a novel 4D demosaicing algorithm based on kernel regression is also proposed. Our experimental results show that it outperforms the state of art algorithms.

AB - We present a reconstruction algorithm that can restore the captured 4D light field from a portable plenoptic camera without the need for calibration images. An efficient and robust estimator is proposed to accurately detect the centers of microlens images. Based on that estimator, parameters that model the centers of microlens array images are obtained by solving a global optimization problem. To further enhance the quality of reconstructed multi-view images, a novel 4D demosaicing algorithm based on kernel regression is also proposed. Our experimental results show that it outperforms the state of art algorithms.

M3 - Conference Publication

BT - Asian Conference on Computer Vision 2014

CY - Singapore

ER -

Multi-view Image Restoration From Plenoptic Raw Images

Abstract

Authors (Note for portal: view the doc link for the full list of authors)

Fingerprint

Cite this