APSIPA Transactions on Signal and Information Processing > Vol 8 > Issue 1

Deep-learning-based macro-pixel synthesis and lossless coding of light field images

Ionut Schiopu, Vrije Universiteit Brussel (VUB), Belgium, ischiopu@etrovub.be , Adrian Munteanu, Vrije Universiteit Brussel (VUB), Belgium
 
Suggested Citation
Ionut Schiopu and Adrian Munteanu (2019), "Deep-learning-based macro-pixel synthesis and lossless coding of light field images", APSIPA Transactions on Signal and Information Processing: Vol. 8: No. 1, e20. http://dx.doi.org/10.1017/ATSIP.2019.14

Publication Date: 17 Jul 2019
© 2019 Ionut Schiopu and Adrian Munteanu
 
Subjects
 
Keywords
Deep-learningView synthesisLossless image compressionLight field image
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 948 times

In this article:
I. INTRODUCTION 
II. STATE-OF-THE-ART 
III. PROPOSED METHOD 
IV. EXPERIMENTAL EVALUATION 
V. CONCLUSIONS 

Abstract

This paper proposes a novel approach for lossless coding of light field (LF) images based on a macro-pixel (MP) synthesis technique which synthesizes the entire LF image in one step. The reference views used in the synthesis process are selected based on four different view configurations and define the reference LF image. This image is stored as an array of reference MPs which collect one pixel from each reference view, being losslessly encoded as a base layer. A first contribution focuses on a novel network design for view synthesis which synthesizes the entire LF image as an array of synthesized MPs. A second contribution proposes a network model for coding which computes the MP prediction used for lossless encoding of the remaining views as an enhancement layer. Synthesis results show an average distortion of 29.82 dB based on four reference views and up to 36.19 dB based on 25 reference views. Compression results show an average improvement of 29.9% over the traditional lossless image codecs and 9.1% over the state-of-the-art.

DOI:10.1017/ATSIP.2019.14