The chapter will cover deep learning methodologies that can be employed to recover image and video quality. Most of the covered approaches will be based on conditional Generative Adversarial Networks (GAN) which have the benefit to produce images which look more natural. Looking at the inference phase we will show how to perform such operations with a low computational footprint. Regarding the training phase we will address in depth architectural choices, loss functions and training strategies in general. Finally, we will also deal with settings in which there is the possibility to control both end of the image transmission pipeline.
Improving Video Quality with Generative Adversarial Networks
Tiberio Uricchio;
2021-01-01
Abstract
The chapter will cover deep learning methodologies that can be employed to recover image and video quality. Most of the covered approaches will be based on conditional Generative Adversarial Networks (GAN) which have the benefit to produce images which look more natural. Looking at the inference phase we will show how to perform such operations with a low computational footprint. Regarding the training phase we will address in depth architectural choices, loss functions and training strategies in general. Finally, we will also deal with settings in which there is the possibility to control both end of the image transmission pipeline.File | Dimensione | Formato | |
---|---|---|---|
978-3-030-74478-6 (1).pdf
solo utenti autorizzati
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati
Dimensione
491.56 kB
Formato
Adobe PDF
|
491.56 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.