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.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    embedGAN: A Method to Embed Images in GAN Latent Space


    Beteiligte:
    Yuan, Philip F. (Herausgeber:in) / Yao, Jiawei (Herausgeber:in) / Yan, Chao (Herausgeber:in) / Wang, Xiang (Herausgeber:in) / Leach, Neil (Herausgeber:in) / Chen, Zhijia (Autor:in) / Huang, Weixin (Autor:in) / Luo, Ziniu (Autor:in)

    Kongress:

    The International Conference on Computational Design and Robotic Fabrication ; 2020 ; Shanghai, China July 05, 2020 - July 06, 2020


    Erschienen in:

    Erscheinungsdatum :

    2021-01-29


    Format / Umfang :

    9 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch