Iterative multiscale image generation using neural networks

A method of generating an output image having an output resolution of N pixels×N pixels, each pixel in the output image having a respective color value for each of a plurality of color channels, the method comprising: obtaining a low-resolution version of the output image; and upscaling the low-reso...

Full description

Saved in:
Bibliographic Details
Main Authors Colmenarejo, Sergio Gomez, van den Oord, Aaron Gerard Antonius, Gomes de Freitas, Joao Ferdinando, Belov, Daniel, Kalchbrenner, Nal Emmerich, Reed, Scott Ellison, Wang, Ziyu
Format Patent
LanguageEnglish
Published 22.08.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A method of generating an output image having an output resolution of N pixels×N pixels, each pixel in the output image having a respective color value for each of a plurality of color channels, the method comprising: obtaining a low-resolution version of the output image; and upscaling the low-resolution version of the output image to generate the output image having the output resolution by repeatedly performing the following operations: obtaining a current version of the output image having a current K×K resolution; and processing the current version of the output image using a set of convolutional neural networks that are specific to the current resolution to generate an updated version of the output image having a 2K×2K resolution.
Bibliography:Application Number: US202217751359