IMAGE GENERATION USING ONE OR MORE NEURAL NETWORKS

Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, at least a first optical flow network (OFN) and at least a first reconstruction network (RN) can be used to generate one or more images based, at least in part, upon the OFN and the RN using a shared l...

Full description

Saved in:
Bibliographic Details
Main Authors SALVI, Marco, LEFOHN, Aaron, SHACKLETT, Brennan
Format Patent
LanguageEnglish
French
Published 07.04.2022
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:Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, at least a first optical flow network (OFN) and at least a first reconstruction network (RN) can be used to generate one or more images based, at least in part, upon the OFN and the RN using a shared loss function. Des appareils, des systèmes et des techniques de génération d'images sont présentés. Dans au moins un mode de réalisation, au moins un premier réseau de flux optique (OFN) et au moins un premier réseau de reconstruction (RN) peuvent servir à générer une ou plusieurs images sur la base, au moins en partie, de l'OFN et du RN faisant appel à une fonction de perte partagée.
Bibliography:Application Number: WO2021US52951