AUTOMATIC GENERATION OF REALISTIC CITY IMAGES FROM RARE DATASET USING GAN ENHANCED WITH TRANSFER LEARNING

DOI

Bibliographic Information

Other Title
  • 転移学習で強化したGANによる稀少データから写実的な都市画像の自動生成
Published
2022
Resource Type
journal article
DOI
  • 10.11532/jsceiii.3.j2_551
Publisher
Japan Society of Civil Engineers

Description

<p>There has been a growing demand to strengthen existing disaster prevention education tobe prepared for the huge tsunami expected to occur in the near future. Virtual reality, which allows people to virtually experience natural disasters, has a strong potential in fostering disaster awareness among citizens. However, it requires enormous human and time resources to map the texture of structures to urban area-imitating virtual space. On the other hand, pix2pixHD proposed by Wang et al. can generate high-resolution synthetic images by learning from reference images, label data, and object boundary data. In this study, we applied pix2pixHD and transfer learning, which diverts networks trained on other similar domains, to verify texture mapping of urban areas in Japan from a limited set of image data.</p>

Journal

Related Projects

See more

Keywords

Details 詳細情報について

  • CRID
    1390012638715522560
  • DOI
    10.11532/jsceiii.3.j2_551
  • ISSN
    24359262
  • Text Lang
    ja
  • Article Type
    journal article
  • Data Source
    • JaLC
    • KAKEN
  • Abstract License Flag
    Disallowed

Report a problem

Back to top