Logo DOAB
  • Connection pour éditeurs
    • Support
    • Language 
      • English
      • français
    • Deposit
            Voir le document 
            •   Accueil de DSpace
            • Voir le document
            •   Accueil de DSpace
            • Voir le document
            JavaScript is disabled for your browser. Some features of this site may not work without it.

            Chapter Generative Design Intuition from the Fine-Tuned Models of Named Architects’ Style

            Thumbnail
            Auteur
            Jeong, Hyun
            Yoo, Youngjin
            Kim, Youngchae
            Cha, SeungHyun
            Lee, Jin-Kook
            Language
            English
            Afficher la notice complète
            Résumé
            This paper suggests the potential application of generative artificial intelligence-based image generation technology in the field of architecture, for early phase shape planning, using the styles of renowned architects. The study employed the following approaches: 1) Intensive image generation based on the styles of 20 architects to test the AI's recognition ability and image quality. 2) Additional training was conducted for architects with low recognition rates to construct an enhanced learning model in the quality of image generation. 3) In addition to generating architectural visualization images using existing architects' design styles, alternative styles were proposed through design combinations, aiming to concretize ambiguous idea communication in the early stages of design and enhance its efficiency. The study sheds light on the future prospects of applying this generative AI model in the field of architecture
            URI
            https://doab-dev.siscern.org/handle/20.500.12854/179869
            Keywords
            Design Style of Architects; Generative AI; Image Generation; Fine-tuning; thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence
            DOI
            10.36253/979-12-215-0289-3.91
            ISBN
            9791221502893
            Publisher
            Firenze University Press
            Publisher website
            www.fupress.com/
            Publication date and place
            Florence, 2023
            Series
            Proceedings e report,
            Pages
            9
            • OAPEN harvesting collection

            Parcourir

            Tout DSpaceSubjectsPublishersLanguagesCollections

            Mon compte

            Ouvrir une sessionS'inscrire

            Export

            Repository metadata
            Doabooks

            • For Researchers
            • For Librarians
            • For Publishers
            • Our Supporters
            • Resources
            • DOAB

            Newsletter


            • subscribe to our newsletter
            • view our news archive

            Follow us on

            • Twitter

            License

            • If not noted otherwise all contents are available under Attribution 4.0 International (CC BY 4.0)

            donate


            • Donate
              Support DOAB and the OAPEN Library

            Credits


            • logo Investir l'avenirInvestir l'avenir
            • logo MESRIMESRI
            • logo EUEuropean Union
              This project received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871069.

            Directory of Open Access Books is a joint service of OAPEN, OpenEdition, CNRS and Aix-Marseille Université, provided by DOAB Foundation.

            Websites:

            DOAB
            www.doabooks.org

            OAPEN Home
            www.oapen.org

            OAPEN OA Books Toolkit
            www.oabooks-toolkit.org

            Export search results

            The export option will allow you to export the current search results of the entered query to a file. Differen formats are available for download. To export the items, click on the button corresponding with the preferred download format.

            A logged-in user can export up to 15000 items. If you're not logged in, you can export no more than 500 items.

            To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

            After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.