The Letter introduces a novel filtering method based on convolutional neural networks (CNNs) for quality enhancement of light field (LF) images captured by a plenoptic camera and compressed using high-efficiency video coding (HEVC). The method takes advantage of the macro-pixel (MP) structure specific to the LF images and proposes a novel MP-wise filtering approach based on a novel deep neural network architecture. The proposed CNN-based method achieves an outstanding performance when HEVC is employed without its in-loop filters. Experimental results show high luminance-peak signal-to-noise ratio (Y-PSNR) gains and average Y-Bjøntegaard delta (BD)-rate savings of 25.6% over HEVC on a large data set.
Huang, H, Schiopu, I & Munteanu, A 2020, ' Macro-pixel-wise CNN-based filtering for quality enhancement of light field images ', Electronics Letters , vol. 56, no. 25, el.2020.2344 , pp. 1413-1416.
Huang, H., Schiopu, I. , & Munteanu, A. (2020). Macro-pixel-wise CNN-based filtering for quality enhancement of light field images . Electronics Letters , 56 (25), 1413-1416. [el.2020.2344 ].
@article{1aa3bba773a1485e8c5163f341cad032,
title = " Macro-pixel-wise CNN-based filtering for quality enhancement of light field images " ,
abstract = " The Letter introduces a novel filtering method based on convolutional neural networks (CNNs) for quality enhancement of light field (LF) images captured by a plenoptic camera and compressed using high-efficiency video coding (HEVC). The method takes advantage of the macro-pixel (MP) structure specific to the LF images and proposes a novel MP-wise filtering approach based on a novel deep neural network architecture. The proposed CNN-based method achieves an outstanding performance when HEVC is employed without its in-loop filters. Experimental results show high luminance-peak signal-to-noise ratio (Y-PSNR) gains and average Y-Bj{o}ntegaard delta (BD)-rate savings of 25.6% over HEVC on a large data set. " ,
keywords = " Deep Learning, Quality Enhancement, Light field image, HEVC " ,
author = " Hongyue Huang and Ionut Schiopu and Adrian Munteanu " ,
year = " 2020 " ,
month = nov,
day = " 4 " ,
doi = " 10.1049/el.2020.2344 " ,
language = " English " ,
volume = " 56 " ,
pages = " 14131416 " ,
journal = " Electronics Letters " ,
issn = " 0013-5194 " ,
publisher = " Institution of Engineering and Technology " ,
number = " 25 " ,
}