• 한국실내디자인학회논문집
• /
• 제20권1호
• /
• pp.89-97
• /
• 2011

Furniture design is no exception to human desire for pursuit of the nature. In various design fields, it has turned out nature-decorative method in the past, and also recently it has turned out bio-adaptive method which is more root design process using principal of generation in nature world. The purpose of this study is to analyze application methods and characteristics of fractal geometry and voronoi diagram which are most representative principals of generative design in nature by research on the example of furniture design using these principals. The results of having analyzed fumitures by generative design can be summarized as follows; design principals of fractal; superposition, scaling, repetition & gradation, deformation, distortion and voronoi diagram; individual speciation, variational patten, repetition gradation, ambiguous boundary create new design concept and emergent form in furniture design. Application methods are 'form emergence by algorithm', 'conventional process based on principals of generative design', and 'reproduction of pattern from generative design'. Biological reinterpretations and new explorations of principals of nature generation offer unbounded possibilities for furniture design.

• 복식
• /
• 제67권4호
• /
• pp.58-70
• /
• 2017

This study examined the characteristics of generative design methodology, and it selected and analyzed 11 sites that provide design development services using generative methodology, INPUT data were classified into design form factor based on the choices of each and the variable form associated with each participant's movement. In designing the algorithms, designers set the meth- od and range of participation according to the characteristics of the design, and linked them with design components. This provided the study with a discriminative design process. This resulted in a type with morphological characteristics and a type that emphasized epidermal formability. The generative design methodology has value as an alternative process in the field of fashion where the utilization of digital technology is becoming universal based on contingency and variability. The results of this study can be used as basic data for the study of personalized design through the extension of methodology of digital-based fashion design and generative methodology.

• 한국의류학회지
• /
• 제41권5호
• /
• pp.825-839
• /
• 2017

Generative Art (also called as the art of the algorithm) creates unexpected results, moving autonomously according to rules or algorithms. The evolution of digital media in art, which tries to seek novelty, increases the possibility of new artistic fields; subsequently, this study establishes the basis for new design approaches by analyzing visual cases of Generative Art that have emerged since the 20th century and characteristics expressed on fashion. For the methodology, the study analyzes fashion designs that have emerged since 2000, based on theoretical research that includes literature and research papers relating to Generative Art. According to the study, expression characteristics shown in fashion, based on visual properties of Generative Art, are as follows. First, abstract randomness is expressed with unexpected coincidental forms using movements of a creator and properties of materials as variables in accordance to rules or algorithms. Second, endlessly repeated pattern imitation expresses an emergent shape by endless repetition created by a modular system using rules or 3D printing using a computer algorithm. Third, the systematic variability expresses constantly changing images with a combination of system and digital media by a wearing method. It is expected that design by algorithm becomes a significant method in producing other creative ideas and expressions in modern fashion.

• 한국BIM학회 논문집
• /
• 제14권2호
• /
• pp.13-24
• /
• 2024

This research suggests a novel visualization approach utilizing Generative AI to render photorealistic architectural alternatives images in the early design phase. Photorealistic rendering intuitively describes alternatives and facilitates clear communication between stakeholders. Nevertheless, the conventional rendering process, utilizing 3D modelling and rendering engines, demands sophisticate model and processing time. In this context, the paper suggests a rendering approach employing the text-to-image method aimed at generating a broader range of intuitive and relevant reference images. Additionally, it employs an Text-to-Image method focused on producing a diverse array of alternatives reflecting architects' styles when visualizing the exteriors of residential buildings from the mass model images. To achieve this, fine-tuning for architects' styles was conducted using the Low-Rank Adaptation (LoRA) method. This approach, supported by fine-tuned models, allows not only single style-applied alternatives, but also the fusion of two or more styles to generate new alternatives. Using the proposed approach, we generated more than 15,000 meaningful images, with each image taking only about 5 seconds to produce. This demonstrates that the Generative AI-based visualization approach significantly reduces the labour and time required in conventional visualization processes, holding significant potential for transforming abstract ideas into tangible images, even in the early stages of design.

• 한국전자통신학회논문지
• /
• 제18권2호
• /
• pp.349-354
• /
• 2023

최근 인테리어에 관심을 가지는 인구가 증가함에 따라 세계적으로 인테리어 시장이 크게 성장하고 있으며, 글로벌 인테리어 업체들은 다양한 인테리어 요소에 대한 시뮬레이션 서비스를 개발하여 제공하고 있다. 벽지의 디자인은 가장 중요한 인테리어 요소임에도 불구하고, 기존 벽지 디자인 시뮬레이션 서비스들은 예상되는 결과물과 실제 결과물 간 차이, 긴 시뮬레이션 작업시간, 전문적인 기술의 필요 등의 단점으로 인해 사용에 어려움이 있다. 본 논문에서는 벽지 인테리어 시뮬레이션을 위한 Cycle GAN(: Generative Adversarial Networks) 기반의 벽지 이미지 변환 기법을 제안한다. 제안하는 기법은 다양한 모양의 벽지가 사용된 인테리어 이미지 데이터를 기반으로 모델을 학습하여, 사용자에게 짧은 시간 내에 벽지 인테리어 시뮬레이션을 제공할 수 있다.

• 한국지능시스템학회논문지
• /
• 제24권3호
• /
• pp.233-238
• /
• 2014

독창성은 예술작품 뿐만아니라 장신구, 생활용품 등 다양한 디자인에서 요구된다. 창조적 디자인 작업에 참신한 모티프를 얻기 위해 변환생성 디자인 기법이 활용될 수 있다. 이 논문에서는 유전자 알고리즘을 이용하여 독특한 반지 모델을 만들어 내는 변환생성 디자인 방법을 제안한다. 후보해 표현방법, 연산자, 평가함수 관점에서 제안된 알고리즘에 대해서 소개한다. 제안한 방법은 고객이 자신의 반지 모양에 대한 취향을 선택하도록 하고, 취향을 평가에 반영하도록 하면서 여러 가지 반지 모델을 만들어서 추천하도록 한다. 반지 모델은 3차원 입체로 표현되기 때문에, 고객이 최종적으로 선택한 모델을 3차원 프린터를 통해서 실물로 제작될 수 있다.

• 한국주거학회논문집
• /
• 제19권1호
• /
• pp.9-16
• /
• 2008

This study aims to construct the design competence by means of a topological approach. To this end, the linguistic concept of 'competence and performance' in Chomskian sense is borrowed and applied to the study. The usability of this method is then tested against the sample apartment plans from Gangnam-gu area in Seoul, and it is found that this enabled a middle-ground approach to a more productive grammar that overcomes the limits in Glassie's and Stiny's grammar systems. Through a series of analyses on the sample plans, it could be clarified that there appear classificatory levels in the competence that controls the planning of the building, zoning of the unit, and layout of LDK combination. At the end, it is evaluated that the generative grammar, constructed in this research, is the possible world in designers' minds, and this retrospective remodelling of the architectural competence could illuminate the 'design decision flow' that generates the sample plans.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1761-1777
• /
• 2021

An image with infrared features and visible details is obtained by processing infrared and visible images. In this paper, a fusion method based on Laplacian pyramid and generative adversarial network is proposed to obtain high quality fusion images, termed as Laplacian-GAN. Firstly, the base and detail layers are obtained by decomposing the source images. Secondly, we utilize the Laplacian pyramid-based method to fuse these base layers to obtain more information of the base layer. Thirdly, the detail part is fused by a generative adversarial network. In addition, generative adversarial network avoids the manual design complicated fusion rules. Finally, the fused base layer and fused detail layer are reconstructed to obtain the fused image. Experimental results demonstrate that the proposed method can obtain state-of-the-art fusion performance in both visual quality and objective assessment. In terms of visual observation, the fusion image obtained by Laplacian-GAN algorithm in this paper is clearer in detail. At the same time, in the six metrics of MI, AG, EI, MS_SSIM, Q_abf and SCD, the algorithm presented in this paper has improved by 0.62%, 7.10%, 14.53%, 12.18%, 34.33% and 12.23%, respectively, compared with the best of the other three algorithms.

• 복식
• /
• 제63권7호
• /
• pp.134-147
• /
• 2013

Today, the convergence of fashion design and digital technology has become a popular method and accordingly been tried variously in the fashion area. This study aimed to analyze the character of the collaboration with fashion and technology, and the meaning of technology as emotional expression methods. Selected designer's collections, literature and other related studies were reviewed in order to analyze the generative structure of the meaning and the binary-opposition in the convergence of body, fashion design and technology. Literatures and selected designer's collections were reviewed and quantitatively studies were performed to classify the convergence of human bodies, fashion design and technology through Greimas Semiotics rectangle based on binary-opposition of meaning and isotophy analysis. The research presents three types of fashion technology methods: mechanical movement, light/digital media, and virtual image. The convergence of fashion and technology was classified as the direct convergence and the indirect convergence. The direct convergence was characterized by variability and has automatic, independent movement, but the indirect convergence was shown closed and to have contradistinctive images.

• 한국실내디자인학회논문집
• /
• 제23권4호
• /
• pp.129-139
• /
• 2014

The objective of this research is to suggest new geometric possibilities in digital architecture by investigating the characteristics of hybridization in digital geometry. The research begins with theoretical background research such as defining hybridization, investigating hybrid thinking, and studying the theory of digital geometry, along with the four conceptual characteristics of hybridization that could be drawn, such as temporality, liquidity, complexity, and connectivity. Based on these characteristics, the generative method of hybrid digital geometric languages such as Blob, Particle, Morph, Loft, and Boolean was analyzed with case research in contemporary digital architecture. As a result, diverse hybrid geometric keywords were extracted; these keywords suggest potential meanings of hybridization such as accidentality, mobility, diversity, and identity. Different elements represent the "mobility" in time by the force and wave, and they are "accidentally" combined in gradual change. The united species in "diverse" characters are seamlessly connected and emerge as a new "identity." The research maximizes the generative possibilities in digital geometry and provides a theoretical basis to apply the digital hybrid methods to architectural design by suggesting the potential meanings and possibilities in hybridization.