Accès chercheur

EEDIS Laboratory

Evolutionary Engineering

and

Distributed Information Systems

Réseaux et Communication

Sécurité et Multimédia

Ingénierie des Connaissances

Data Mining & Web Intelligent

Interopérabilité des Systèmes d’information
& Bases de données

Développement Orienté Service

RDO-Based Light Field Image Coding Using Convolutional Neural Networks and Linear Approximation

Auteurs: » Bakir Nader
» Hamidouche Wassim
» Deforges Olivier
» Samrout Khouloud
» Khalil Mohamad
Type : Conférence Internationale
Nom de la conférence : DCC
Lieu : Pays:
Lien : »
Publié le : 26-03-2019

The increasing penetration of acquisition and display devices for Light Field (LF) content in the consumer market leads to the high proliferation of this new immersive media. This growing interest to LF images thus urgently raises the question of their compression. In this paper, we propose a convolutional neural networks (CNN)-based LF image coding scheme including both Rate Distortion Optimization (RDO) and post-processing steps. First, at the encoder side, the views are rearranged in sparse set of views and dropped views sets. The former are compressed with a standard encoder and transmitted, while the dropped views are either linearly approximated or synthesized by a CNN using the encoded views as input. This choice is made on the basis of the proposed RDO process. At the decoder side, once the dropped views are either linearly approximated or synthesized by a CNN block, a post-processing step is performed to further enhance the quality of the reconstructed views. This post-processing block is based on superpixel to pixel-matching. Experimental results show that the proposed scheme provides views with high visual quality and overcomes the state-of-the-art LF image compression solutions by− 30% in terms of BD-BR and 0.62 dB in BD-PSNR.

Tous droits réservés - © 2019 EEDIS Laboratory