Image compression using normalizing flows

According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Helminger, Leonhard Markus, Xue, Yuanyi, Schroers, Christopher Richard, McPhillen, Jared, Djelouah, Abdelaziz, Doggett, Erika Varis, Labrozzi, Scott
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image, and quantize the latent space representation of the input image to produce multiple quantized latents. The hardware processor further executes the software code to encode the quantized latents using a probability density function of the latent space representation of the input image, to generate a bitstream, and convert the bitstream into an output image corresponding to the input image. The probability density function of the latent space representation of the input image is obtained based on a normalizing flow mapping of one of the input image or the latent space representation of the input image.