Objective Image Quality Analysis of Convolutional Neural Network Light Field Coding

Light field digital images are novel image modalities for capturing a sampled representation of the plenoptic function. A large amount of data is typically associated to a single sample of a scene, and data compression tools are required in order to develop systems and applications for light field c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:European Workshop on Visual Information Processing s. 163 - 168
Hlavní autoři: Medda, Daniele, Song, Wei, Perra, Cristian
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2019
Témata:
autoen-coder
Codecs
coding
compression
Convolution
convolutional neural network
Encoding
Image coding
image quality
light field
Measurement
Neural networks
Transform coding
ISSN:2471-8963
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Light field digital images are novel image modalities for capturing a sampled representation of the plenoptic function. A large amount of data is typically associated to a single sample of a scene, and data compression tools are required in order to develop systems and applications for light field communications. This paper presents the study of the performance of a convolutional neural network autoencoder as a tool for digital light field image compression. Testing conditions and a framework for the experimental evaluation are proposed for this study. Different encoders and coding conditions are taken into consideration, obtained results are reported and critically discussed.
ISSN:2471-8963
DOI:10.1109/EUVIP47703.2019.8946230