TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Light Field Reconstruction Using Shearlet Transform

Tutkimustuotosvertaisarvioitu

Standard

Light Field Reconstruction Using Shearlet Transform. / Vagharshakyan, Suren; Bregovic, Robert; Gotchev, Atanas.

julkaisussa: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vuosikerta 40, Nro 1, 2018, s. 133-147.

Tutkimustuotosvertaisarvioitu

Harvard

Vagharshakyan, S, Bregovic, R & Gotchev, A 2018, 'Light Field Reconstruction Using Shearlet Transform', IEEE Transactions on Pattern Analysis and Machine Intelligence, Vuosikerta. 40, Nro 1, Sivut 133-147. https://doi.org/10.1109/TPAMI.2017.2653101

APA

Vagharshakyan, S., Bregovic, R., & Gotchev, A. (2018). Light Field Reconstruction Using Shearlet Transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(1), 133-147. https://doi.org/10.1109/TPAMI.2017.2653101

Vancouver

Vagharshakyan S, Bregovic R, Gotchev A. Light Field Reconstruction Using Shearlet Transform. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018;40(1):133-147. https://doi.org/10.1109/TPAMI.2017.2653101

Author

Vagharshakyan, Suren ; Bregovic, Robert ; Gotchev, Atanas. / Light Field Reconstruction Using Shearlet Transform. Julkaisussa: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018 ; Vuosikerta 40, Nro 1. Sivut 133-147.

Bibtex - Lataa

@article{fa7aabf392b148eeae8bd028808a5e86,
title = "Light Field Reconstruction Using Shearlet Transform",
abstract = "In this article we develop an image based rendering technique based on light field reconstruction from a limited set of perspective views acquired by cameras. Our approach utilizes sparse representation of epipolar-plane images (EPI) in shearlet transform domain. The shearlet transform has been specifically modified to handle the straight lines characteristic for EPI. The devised iterative regularization algorithm based on adaptive thresholding provides high-quality reconstruction results for relatively big disparities between neighboring views. The generated densely sampled light field of a given 3D scene is thus suitable for all applications which require light field reconstruction. The proposed algorithm compares favorably against state of the art depth image based rendering techniques and shows superior performance specifically in reconstructing scenes containing semi-transparent objects.",
author = "Suren Vagharshakyan and Robert Bregovic and Atanas Gotchev",
year = "2018",
doi = "10.1109/TPAMI.2017.2653101",
language = "English",
volume = "40",
pages = "133--147",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE COMPUTER SOC",
number = "1",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Light Field Reconstruction Using Shearlet Transform

AU - Vagharshakyan, Suren

AU - Bregovic, Robert

AU - Gotchev, Atanas

PY - 2018

Y1 - 2018

N2 - In this article we develop an image based rendering technique based on light field reconstruction from a limited set of perspective views acquired by cameras. Our approach utilizes sparse representation of epipolar-plane images (EPI) in shearlet transform domain. The shearlet transform has been specifically modified to handle the straight lines characteristic for EPI. The devised iterative regularization algorithm based on adaptive thresholding provides high-quality reconstruction results for relatively big disparities between neighboring views. The generated densely sampled light field of a given 3D scene is thus suitable for all applications which require light field reconstruction. The proposed algorithm compares favorably against state of the art depth image based rendering techniques and shows superior performance specifically in reconstructing scenes containing semi-transparent objects.

AB - In this article we develop an image based rendering technique based on light field reconstruction from a limited set of perspective views acquired by cameras. Our approach utilizes sparse representation of epipolar-plane images (EPI) in shearlet transform domain. The shearlet transform has been specifically modified to handle the straight lines characteristic for EPI. The devised iterative regularization algorithm based on adaptive thresholding provides high-quality reconstruction results for relatively big disparities between neighboring views. The generated densely sampled light field of a given 3D scene is thus suitable for all applications which require light field reconstruction. The proposed algorithm compares favorably against state of the art depth image based rendering techniques and shows superior performance specifically in reconstructing scenes containing semi-transparent objects.

U2 - 10.1109/TPAMI.2017.2653101

DO - 10.1109/TPAMI.2017.2653101

M3 - Article

VL - 40

SP - 133

EP - 147

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 1

ER -