Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Multiple research studies have recently demonstrated deep networks can generate realistic‐looking textures and stylised images from a single texture example. However, they suffer from some drawbacks. Generative adversarial networks are in general difficult to train. Multiple feature variations, enco...

Popoln opis

Bibliografske podrobnosti
Main Authors: Marek Jakab, Lukas Hudec, Wanda Benesova
Format: Article
Jezik:English
Izdano: Wiley 2020-12-01
Serija:IET Computer Vision
Teme:
Online dostop:https://doi.org/10.1049/iet-cvi.2019.0416