GAN is an efficient generative model. By performing a latent walk in GAN, the generation result can be adjusted. However, the latent walk cannot start from a selected image. The embedGAN is proposed to embed selected images into GAN and remain the generation effect. It contains an embedded network and a generative network. Application cases of residential interior design are given in the article. With advantages of a low computing cost and short training time, embedGAN shows its potential. The embedGAN algorithm framework can be applied to various GANs.
embedGAN: A Method to Embed Images in GAN Latent Space
The International Conference on Computational Design and Robotic Fabrication ; 2020 ; Shanghai, China July 05, 2020 - July 06, 2020
Proceedings of the 2020 DigitalFUTURES ; Kapitel : 20 ; 208-216
2021-01-29
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Embed data security into your IT planning
British Library Online Contents | 2008
|PHOTONIC CRYSTALS: 3-D photonic crystals embed cavities, waveguides
British Library Online Contents | 2008
Europäisches Patentamt | 2023
|Rotterdam Ausstellung. Latent Space
Online Contents | 2002
AIRCRAFT LIGHTING DEVICE CONFIGURED TO EMBED ADDITIONAL FUNCTIONS IN ITS CENTER
Europäisches Patentamt | 2020
|