TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution

Tutkimustuotosvertaisarvioitu

Standard

IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution. / Gao, Yuan; Koch, Reinhard; Bregovic, Robert; Gotchev, Atanas.

2019 27th European Signal Processing Conference (EUSIPCO). IEEE, 2019. (European Signal Processing Conference).

Tutkimustuotosvertaisarvioitu

Harvard

Gao, Y, Koch, R, Bregovic, R & Gotchev, A 2019, IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution. julkaisussa 2019 27th European Signal Processing Conference (EUSIPCO). European Signal Processing Conference, IEEE, EUROPEAN SIGNAL PROCESSING CONFERENCE, 1/01/00. https://doi.org/10.23919/EUSIPCO.2019.8903168

APA

Gao, Y., Koch, R., Bregovic, R., & Gotchev, A. (2019). IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution. teoksessa 2019 27th European Signal Processing Conference (EUSIPCO) (European Signal Processing Conference). IEEE. https://doi.org/10.23919/EUSIPCO.2019.8903168

Vancouver

Gao Y, Koch R, Bregovic R, Gotchev A. IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution. julkaisussa 2019 27th European Signal Processing Conference (EUSIPCO). IEEE. 2019. (European Signal Processing Conference). https://doi.org/10.23919/EUSIPCO.2019.8903168

Author

Gao, Yuan ; Koch, Reinhard ; Bregovic, Robert ; Gotchev, Atanas. / IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution. 2019 27th European Signal Processing Conference (EUSIPCO). IEEE, 2019. (European Signal Processing Conference).

Bibtex - Lataa

@inproceedings{2368356ecc384228acaf87bd59452d0c,
title = "IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution",
abstract = "The performance of a light field reconstruction algorithm is typically affected by the disparity range of the input Sparsely-Sampled Light Field (SSLF). This paper finds that (i) one of the state-of-the-art video frame interpolation methods, i.e. adaptive Separable Convolution (SepConv), is especially effective for the light field reconstruction on a SSLF with a small disparity range (<10 pixels); (ii) one of the state-of-the-art light field reconstruction methods, i.e. Shearlet Transformation (ST), is especially effective in reconstructing a light field from a SSLF with a moderate disparity range (10-20 pixels) or a large disparity range (> 20 pixels). Therefore, to make full use of both methods to solve the challenging light field reconstruction problem on SSLFs with moderate and large disparity ranges, a novel method, referred to as Interpolation-Enhanced Shearlet Transform (IEST), is proposed by incorporating these two approaches in a coarse-to-fine manner. Specifically, ST is employed to give a coarse estimation for the target light field, which is then refined by SepConv to improve the reconstruction quality of parallax views involving small disparity ranges. Experimental results show that IEST outperforms the other state-of-the-art light field reconstruction methods on nine challenging horizontalparallax evaluation SSLF datasets of different real-world scenes with moderate and large disparity ranges.",
keywords = "Light Field Reconstruction, Parallax View Generation, Adaptive Separable Convolution, Shearlet Transform, Interpolation-Enhanced Shearlet Transform",
author = "Yuan Gao and Reinhard Koch and Robert Bregovic and Atanas Gotchev",
year = "2019",
month = "9",
doi = "10.23919/EUSIPCO.2019.8903168",
language = "English",
isbn = "978-1-5386-7300-3",
series = "European Signal Processing Conference",
publisher = "IEEE",
booktitle = "2019 27th European Signal Processing Conference (EUSIPCO)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - IEST: Interpolation-Enhanced Shearlet Transform for Light Field Reconstruction Using Adaptive Separable Convolution

AU - Gao, Yuan

AU - Koch, Reinhard

AU - Bregovic, Robert

AU - Gotchev, Atanas

PY - 2019/9

Y1 - 2019/9

N2 - The performance of a light field reconstruction algorithm is typically affected by the disparity range of the input Sparsely-Sampled Light Field (SSLF). This paper finds that (i) one of the state-of-the-art video frame interpolation methods, i.e. adaptive Separable Convolution (SepConv), is especially effective for the light field reconstruction on a SSLF with a small disparity range (<10 pixels); (ii) one of the state-of-the-art light field reconstruction methods, i.e. Shearlet Transformation (ST), is especially effective in reconstructing a light field from a SSLF with a moderate disparity range (10-20 pixels) or a large disparity range (> 20 pixels). Therefore, to make full use of both methods to solve the challenging light field reconstruction problem on SSLFs with moderate and large disparity ranges, a novel method, referred to as Interpolation-Enhanced Shearlet Transform (IEST), is proposed by incorporating these two approaches in a coarse-to-fine manner. Specifically, ST is employed to give a coarse estimation for the target light field, which is then refined by SepConv to improve the reconstruction quality of parallax views involving small disparity ranges. Experimental results show that IEST outperforms the other state-of-the-art light field reconstruction methods on nine challenging horizontalparallax evaluation SSLF datasets of different real-world scenes with moderate and large disparity ranges.

AB - The performance of a light field reconstruction algorithm is typically affected by the disparity range of the input Sparsely-Sampled Light Field (SSLF). This paper finds that (i) one of the state-of-the-art video frame interpolation methods, i.e. adaptive Separable Convolution (SepConv), is especially effective for the light field reconstruction on a SSLF with a small disparity range (<10 pixels); (ii) one of the state-of-the-art light field reconstruction methods, i.e. Shearlet Transformation (ST), is especially effective in reconstructing a light field from a SSLF with a moderate disparity range (10-20 pixels) or a large disparity range (> 20 pixels). Therefore, to make full use of both methods to solve the challenging light field reconstruction problem on SSLFs with moderate and large disparity ranges, a novel method, referred to as Interpolation-Enhanced Shearlet Transform (IEST), is proposed by incorporating these two approaches in a coarse-to-fine manner. Specifically, ST is employed to give a coarse estimation for the target light field, which is then refined by SepConv to improve the reconstruction quality of parallax views involving small disparity ranges. Experimental results show that IEST outperforms the other state-of-the-art light field reconstruction methods on nine challenging horizontalparallax evaluation SSLF datasets of different real-world scenes with moderate and large disparity ranges.

KW - Light Field Reconstruction

KW - Parallax View Generation

KW - Adaptive Separable Convolution

KW - Shearlet Transform

KW - Interpolation-Enhanced Shearlet Transform

U2 - 10.23919/EUSIPCO.2019.8903168

DO - 10.23919/EUSIPCO.2019.8903168

M3 - Conference contribution

SN - 978-1-5386-7300-3

T3 - European Signal Processing Conference

BT - 2019 27th European Signal Processing Conference (EUSIPCO)

PB - IEEE

ER -