메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(연세대학교) (연세대학교) (연세대학교)
저널정보
(사)한국CDE학회 한국CDE학회 논문집 한국CDE학회 논문집 제29권 제4호
오류 신고하기

피인용 0

검색

    초록·키워드

    This study proposes an automated visualization tool for generating building facade images that reflect local identity, focusing on commercial buildings in the Seoul metropolitan area. The research evaluates existing image generation models and improves them through additional training with region-specific data, ultimately implementing an automated facade image generation tool. The process involved constructing a dataset using street view images, optimizing the model through hyperparameter tuning, and conducting additional training on commercial buildings in Seoul. The developed tool integrates 3D modeling environment with trained models, allowing users to easily create and visualize diverse facade design ideas from basic mass forms. It supports various applications, including initial design phase ideation, renovation project visualization, and region-specific design proposals. By combining Image-to-image generative AI with architectural modeling processes, this research presents a novel approach to architectural visualization. The integration of 3D modeling, building information, and realistic visualization in a single tool streamlines the architectural design process and fosters more informed decision-making in the early stages of design, enhancing communication between designers, clients, and stakeholders, potentially.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-25-02-091219563