Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 784

Reformat results as: short short into frame detailed detailed into frame

_id	ecaade2023_137
id	ecaade2023_137
authors	Blaas, Quintin, Pelosi, Antony and Brown, Andre
year	2023
title	Reconsidering Artificial Intelligence as Co-Designer
doi	https://doi.org/10.52842/conf.ecaade.2023.2.559
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 559–566
summary	The research in this paper is presented from the perspective of a designer interested in investigating using artificial intelligence, specifically machine learning, to act as a co-pilot during architectural design phases. Significant recent interest has been evident in, for instance, rapidly developing text-to-image and intelligent chat AI areas. However, we have a particular focus and have undertaken a series of feasibility experiments to explore the potential for enabling a designer's exploitation of machine learning, and consequently in effect, using machine learning as a co-designer. We conclude that the industry would need to develop certain protocols to take advantage of the opportunities available through such an AI-assisted approach.
keywords	Artificial Intelligence, Design Data, Algorithmic Design, Design Process, Co-Designing
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_48
id	ecaade2023_48
authors	Doumpioti, Christina and Huang, Jeffrey
year	2023
title	Text to Image to Data
doi	https://doi.org/10.52842/conf.ecaade.2023.2.541
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 541–548
summary	Recent advancements in text-to-image technology have transformed the landscape of computational creativity by enabling the generation of conceptual images. By implementing innovative standards for image generation, we can now shift our focus from the constraints of notational design communication to more purposeful reflection, opening up new design possibilities for future architectures informed by contemporary ideas, concepts, and concerns. In light of the pressing climatic crisis, this paper specifically explores the relationship between text-to-image generation and the integration of environmental sensibility, aiming to explore how digital information (bits) can translate into physical reality (atoms). Our case study focuses on specific residential building typology and its façade morphology to analyse the environmental responsiveness of the design. We propose a workflow that merges creative and analytic processes, through different stages, including diffusion-generated conceptual images, 2D to 3D through depth-mapping and point-cloud meshing, semantic segmentation analysis and sunlight simulation. The paper describes the methods and their combination into a coherent workflow, outlines encountered setbacks, and suggests stages for further improvement.
keywords	Computational Creativity, Text-to-Image, Simulation, Environmental Responsiveness, Machine Intelligence
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ijac202321202
id	ijac202321202
authors	Koehler, Daniel
year	2023
title	More than anything: Advocating for synthetic architectures within large-scale language-image models
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 242–255
summary	Large-scale language-image (LLI) models have the potential to open new forms of critical practice through architectural research. Their success enables designers to research within discourses that are profoundly connected to the built environment but did not previously have the resources to engage in spatial research. Although LLI models do not generate coherent building ensembles, they offer an esthetic experience of an AI infused design practice. This paper contextualizes diffusion models architecturally. Through a comparison of approaches to diffusion models in architecture, this paper outlines data-centric methods that allow architects to design critically using computation. The design of text-driven latent spaces extends the histories of typological design to synthetic environments including non-building data into an architectural space. More than synthesizing quantic ratios in various arrangements, the architect contributes by assessing new categorical differences into generated work. The architects’ creativity can elevate LLI models with a synthetic architecture, nonexistent in the data sets the models learned from.
keywords	diffusion models, large-scale language-image models, data-centric, access to data, discrete computation, critical computational practice, synthetic architecture
series	journal
last changed	2024/04/17 14:30

_id	acadia23_v2_508
id	acadia23_v2_508
authors	Koehler, Daniel; liu, Zidong
year	2023
title	Exploring Building Typologies and their Socioeconomic Contexts: Compositional Insights from Large-Scale-Text-to-Image Models
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-0-3]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 508-517.
summary	This study utilizes large-scale-text-to-image (LLI) models to investigate possibilities to describe building types data-centric. With the introduction of ""data-centric typologies"" we hope to challenge traditional architectural classification systems, while reviving type as an architectural strategy to link socio-economic contexts to the physical form of a place. By examining artificial intelligence (AI)-generated images of various city buildings, the research explores compositional characteristics, realism, and model limitations. We generated and segmented a synthetic dataset of 15,000 images into individual building segments, conducting a statistical analysis of compositional features across 500 cities. Despite dataset biases and limitations, our results indicate that synthetic databases provide a deeper analytical basis than traditional methods. The generated dataset alone paints forensic landscapes of locales that are not typically showcased. Particularly from a pedagogical perspective, data-centric investigations can serve as a valuable tool for illustrating the diversity of cities and living modes. The findings show that socio-economic attributes, like quality of life, are more closely tied to neighborhoods or projects than entire cities. Consequently, architectural typologies are most effective at a human-ori- ented scale, interfacing city with architecture.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:13

_id	ijac202321203
id	ijac202321203
authors	Kudless, Andrew
year	2023
title	Hierarchies of bias in artificial intelligence architecture: Collective, computational, and cognitive
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 256–279
summary	This paper examines the prevalence of bias in artificial intelligence text-to-image models utilized in the architecture and design disciplines. The rapid pace of advancements in machine learning technologies, particularly in text-to-image generators, has significantly increased over the past year, making these tools more accessible to the design community. Accordingly, this paper aims to critically document and analyze the collective, computational, and cognitive biases that designers may encounter when working with these tools at this time. The paper delves into three hierarchical levels of operation and investigates the possible biases present at each level. Starting with the training data for large language models (LLM), the paper explores how these models may create biases privileging English-language users and perspectives. The paper subsequently investigates the digital materiality of models and how their weights generate specific aesthetic results. Finally, the report concludes by examining user biases through their prompt and image selections and the potential for platforms to perpetuate these biases through the application of user data during training.
keywords	Bias in artificial intelligence, language bias, aesthetic bias, latent diffusion models, digital materiality
series	journal
last changed	2024/04/17 14:30

_id	ecaade2023_266
id	ecaade2023_266
authors	Çiçek, Selen, Turhan, Gözde Damla and Özkar, Mine
year	2023
title	Reconsidering Design Pedagogy through Diffusion Models
doi	https://doi.org/10.52842/conf.ecaade.2023.1.031
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 31–40
summary	The text-to-image based diffusion models are deep learning models that generate images from text-based narratives in user-generated prompts. These models use natural language processing (NLP) techniques to recognize narratives and generate corresponding images. This study associates the assignment-based learning-by-doing of design studio with the prompt-based diffusion models that require fine-tuning in each image generation. The reference is a specific formal education setup developed within the context of compulsory courses in design programs’ curricula. We explore the implications of diffusion models for a model of the basic design studio as a case study. The term basic design implies a core and foundational element of design. To explore and evaluate the potential of AI tools to improve novice designers’ design problem solving capabilities, a retrospective analysis was conducted for a series of basic design studio assignments. The first step of the study was to reframe the assignment briefs as design problems and student design works as design solutions. The outcomes of the identification were further used as input data to generate synthetic design solutions by text-to-image diffusion models. In the third step, the design solution sets generated by students and the diffusion models were comparatively assessed by design experts with regards to how well they answered to the design problems defined in the briefs. The initial findings showed that diffusion models were able to generate a myriad of design solutions in a short time. It is conjectured that this might help students to easily understand the ill-defined design problem requirements and generate visual concepts based on written descriptions. However, the comparison indicated the value of design reasoning conveyed in the studio, as it gets highlighted with the lack of improvement in the learning curve of the diffusion model recorded through the synthetic design process.
keywords	Deep Learning, Diffusion Models, Design Education, Basic Design, Design Problems
series	eCAADe
email
last changed	2023/12/10 10:49

_id	acadia23_v3_49
id	acadia23_v3_49
authors	A. Noel, Vernelle; Dortdivanlioglu, Hayri
year	2023
title	Text-to-image generators: Semiotics, Semantics, Syntax, and Society
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 3: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-1-0]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 24-32.
summary	Text-to-image generators, such as Midjourney, DALL-E, and Stable Diffusion, are becoming increasingly popular. These generators, whose models are trained on large datasets of text-image pairs, often scraped from the web, take text prompts as input, and use them to generate images—text-to-image prompting. In this visual essay, we raise questions about the entanglement of semiotics, semantics, syntax, and society in these text-to-image generator tools. We are intrigued by how these technologies are “intrawoven” with social and cultural contexts. How are their constructions and presentations reconfigurations? How do, or might they, inform pedagogy, theory, methods, and our publics? To explore these questions, we entered six prompts related to the built environment in six different languages, eight months apart in Midjourney (“Midjourney” n.d.). The generated images (Figure 1), require that we ask deep questions of each image, in comparison with each other, across each group of four, and across time (eight months apart). We argue that text-to-image generators call for a rigorous exploration of semiotics, semantics, syntax, and the society, with implications for pedagogy, theory-building, methodologies, and public enlightenment. Furthermore, we assert that these tools can facilitate pertinent questions about the relationships between technology and society. This is just the beginning. For now, we have questions.
series	ACADIA
type	field note
email
last changed	2024/04/17 13:59

_id	ascaad2023_024
id	ascaad2023_024
authors	Afshar, Sepehr; Eshaghi, Sarvin; Kim, Ikhwan; Afshar, Sana
year	2023
title	Leveraging Landscape Architecture and Environmental Storytelling for NextGeneration Gaming Experiences: A Holistic Approach to Virtual World Design
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 639-651.
summary	Designing a virtual environment within a digital game occupies a large part of the design procedure, requiring holistic attention and a broad arrangement of the game constituents. Considering other design disciplines, they occupy a unified design methodology; however, a comprehensive literature review reveals the lack of the intended design methodology in the digital game domain's virtual environment development, despite a currently proposed theoretical methodology trying to dissolve the issue. Hence, this research aims to determine the industry's requirements and provide a set of assets included in current digital games as an initial step of providing such a design methodology for the domain. In this regard, the researchers reverse-engineered ten selected digital games, understanding the current condition of digital games via adopting the mentioned currently available design methodology. This dataset reveals a lack in the assets of the story layer in the recent digital games, despite their focus on being story-based. This dilemma leads to long text or speech conversations between game characters, disrupting the players while following the game. The current design focuses on environmental resources only, however, as a virtual landscape, the story needs to be reinforced to be a balanced and well-designed game. Hence, increasing the ratio of the assets in this layer will advance the games' interactivity. Also, as future work, this data set could pave the way for a digital game industry design tool regarding the virtual environment.
series	ASCAAD
email
last changed	2024/02/13 14:34

_id	ecaade2023_328
id	ecaade2023_328
authors	Andreou, Alexis, Kontovourkis, Odysseas, Solomou, Solon and Savvides, Andreas
year	2023
title	Rethinking Architectural Design Process using Integrated Parametric Design and Machine Learning Principles
doi	https://doi.org/10.52842/conf.ecaade.2023.2.461
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 461–470
summary	Artificial Intelligence (AI) has the potential to process vast amounts of subjective and conflicting information in architecture. However, it has mostly been used as a tool for managing information rather than as a means of enhancing the creative design process. This work proposes an innovative way to enhance the architectural design process by incorporating Machine Learning (ML), a type of Artificial Intelligence (AI), into a parametric architectural design process. ML would act as a mediator between the architects' inputs and the end-users' needs. The objective of this work is to explore how Machine Learning (ML) can be utilized to visualize creative designs by transforming information from one form to another - for instance, from text to image or image to 3D architectural shapes. Additionally, the aim is to develop a process that can generate comprehensive conceptual shapes through a request in the form of an image and/or text. The suggested method essentially involves the following steps: Model creation, Revisualization, Performance evaluation. By utilizing this process, end-users can participate in the design process without negatively affecting the quality of the final product. However, the focus of this approach is not to create a final, fully-realized product, but rather to utilize abstraction and processing to generate a more understandable outcome. In the future, the algorithm will be improved and customized to produce more relevant and specific results, depending on the preferences of end-users and the input of architects.
keywords	End-users, Architects, Mass personalization, Visual programming, Neural Network Algorithm
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_436
id	ecaade2023_436
authors	Bank Stigsen, Mathias, Moisi, Alexandra, Rasoulzadeh, Shervin, Schinegger, Kristina and Rutzinger, Stefan
year	2023
title	AI Diffusion as Design Vocabulary - Investigating the use of AI image generation in early architectural design and education
doi	https://doi.org/10.52842/conf.ecaade.2023.2.587
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 587–596
summary	This paper investigates the potential of Text-to-Image AI in assisting the ideation phase in architectural design and education. The study proposes a structured workflow and tests it with first-year architecture students. It aims to create a comprehensive design vocabulary by using AI-generated images as primary design references and incorporating them into a modelling workflow. The paper implements a process combining specific vocabulary extraction, image generation, 2D to 3D translation, and spatial composition within a six weeklong design course. The findings suggest that such a process can enhance the ideation phase by generating new and diverse design inspirations, improve spatial understanding through the exploration of various design elements, and provide students with a targeted visual vocabulary that helps define design intention and streamlines the modelling process.
keywords	Artificial Intelligence, Text-to-Image, Midjourney, Architectural design, Design ideation, 2D to 3D
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2023_90
id	sigradi2023_90
authors	Codarin, Sara and Daubmann, Karl
year	2023
title	Rom[AI]nterrotta
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 705–716
summary	This contribution presents the outcomes of a three-credit elective course offered at Lawrence Technological University’s College of Architecture and Design that involved a week-long travel experience in Rome with undergraduate and graduate students. The course used on-the-fly digital synthetic creations with AI text-to-image and image-to-image generation. The students collectively produced a disciplinary design-fiction tour book for a futuristic Rome, integrated into the city's historical layers. Inspired by the 1978 Roma Interrotta/Interrupted Rome project, the students reimagined the city using AI-informed storytelling to create altered narratives that explored common themes and critical insights. The digital tools allowed students to seamlessly blend AI-generated ideas with photos from the tour, linking historical contexts and contemporary design proposals. The critical use of AI served as a valuable tool in this process, educating designers on the importance of site-specific considerations and capturing the essence of a place through innovative creations informed by their experiences.
keywords	AI, Text-to-Image, Storytelling, Travel Experience, Rome
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	sigradi2023_435
id	sigradi2023_435
authors	Conceiçao, Sandro, Diehl, Natália and Bruscato, Leia
year	2023
title	ChatGPT for Briefing Creation
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 819–830
summary	This study aims to investigate the stages involved in document creation during the architecture and design project phases, through the integration of the Briefing with the assistance of ChatGPT-3.5, with the purpose of assessing the relevance, correspondence, and coherence of data generated by Artificial Intelligence (AI). The research involved the use of two distinct prompts: one featuring a more generic nature, and the other defined by a higher level of detail. It was found that the generic prompt yielded innovative options – not foreseen in the reference sources –, however with lower correspondence. The detailed request was limited to the predefined structure, resulting in greater correspondence and partial consistency with the parameters established in the reference literature. It was possible to conclude that, while AI automates the briefing stages, the input and critical analysis of the generated text require substantial subject knowledge for consistent results.
keywords	Artificial Intelligence, ChatGPT, Briefing, Architecture Programme, Design Process.
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	ecaade2023_145
id	ecaade2023_145
authors	Dortheimer, Jonathan, Schubert, Gerhard, Dalach, Agata, Brenner, Lielle Joy and Martelaro, Nikolas
year	2023
title	Think AI-side the Box! Exploring the Usability of text-to-image generators for architecture students
doi	https://doi.org/10.52842/conf.ecaade.2023.2.567
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 567–576
summary	This study examines how architecture students use generative AI image generating models for architectural design. A workshop was conducted with 25 participants to create designs using three state-of-the-art generative diffusion models and BIM or 3D modeling software. Results showed that the participants found the image-generating models useful for the preliminary design stages but had difficulty when the design advanced because the models did not perform as they expected. Finally, the study shows areas for improvement that merit further research. The paper provides empirical evidence on how generative diffusion models are used in an architectural context and contributes to the field of digital design.
keywords	Machine Learning, Diffusion Models, Design Process, Computational Creativity
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ascaad2023_071
id	ascaad2023_071
authors	Gabr, Rana
year	2023
title	Exploring the Integration of Mid-Journey AI for Architectural Post-Occupancy Evaluation - Prioritizing Experiential Assessment: Case Study of the Egyptian Museum and National Museum of Egyptian Civilization
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 518-550.
summary	The post-occupancy evaluation (POE) process, traditionally reliant on subjective user feedback and observations, has evolved in response to global concerns like climate change and sustainability. This shift towards greater objectivity and quantification reflects an increased focus on precise measurement of environmental and performance metrics. Consequently, architectural assessment is now more quantitatively oriented, moving away from a predominantly experiential emphasis. This research investigates the integration of the emerging AI tool Mid-journey into the POE process, specifically targeting the evaluation of experiential aspects in architectural design. It proposes that AI tools can be instrumental for architects and evaluators by translating user feedback into visual representations and conceptual insights. The study aims to initiate a discourse on the role of text-to-image models in assessing user experiences, potentially becoming integral to the design and concept generation process. The research combines quantitative methods like surveys and AI-driven experiments with qualitative approaches such as observations and interviews to offer enhancement proposals for Egyptian museums, comparing traditional POE solutions and frameworks with new proposed framework that incorporates AI-generated alternatives. This study emphasizes the dual role of museums as artifact custodians and platforms for public education about ancient cultures. It highlights the imperative to transform Egyptian national museums into immersive learning environments, rather than mere storage spaces. The aspiration is to create museums that securely display and preserve artifacts while fostering educational engagement in preserving our shared history.
series	ASCAAD
email
last changed	2024/02/13 14:40

_id	ecaade2023_444
id	ecaade2023_444
authors	Gan, Amelia Wen Jiun, Dang, Quoc, Western, Blaine and García del Castillo, Jose Luis
year	2023
title	AI-Mediated Group Ideation
doi	https://doi.org/10.52842/conf.ecaade.2023.2.389
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 389–398
summary	Design charrettes and town hall formats are commonly used in the field of architecture to facilitate group ideation at multiple stages across a variety of stakeholders. Group ideation is critical to generate a wide range of solutions while covering all aspects of a defined problem. However, the format of group ideation often poses a multitude of challenges, including a lack of diverse ideation, difficulties in reaching consensus, imbalanced power dynamics, as well as maintaining focus throughout a group session. This paper explores how recent developments in AI frameworks could be utilized and assembled as a creative mediator in an architectural ideation process. The paper describes a framework and digital interface for AI-mediated group ideation where recent advancements in speech recognition, Natural Language Processing and Text-to-Image generation are leveraged to facilitate brainstorming processes. The paper first delves into the design of the framework and digital interface, taking into account in-person, remote and hybrid contexts, followed by the technical workflow and pilot evaluation methods used in this study. The resulting design is informed by AI-Mediated Communication, group dynamics and behavioral theories, along with core User Experience principles. The result takes the form of a visual ideation and transcription tool that allows users to ideate across conversational and visual methods.
keywords	AI-Mediated Communication, Ideation, Design Thinking, Natural Language Processing, Human-Computer Interaction
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_446
id	caadria2023_446
authors	Guida, George
year	2023
title	Multimodal Architecture: Applications of Language in a Machine Learning Aided Design Process
doi	https://doi.org/10.52842/conf.caadria.2023.2.561
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 561–570
summary	Recent advances in Natural Language Processing (NLP) and Diffusion Models (DMs) are leading to a significant change in the way architecture is conceived. With capabilities that surpass those of current generative models, it is now possible to produce an unlimited number of high-quality images (Dhariwal and Nichol 2021). This opens up new opportunities for using synthetic images and marks a new phase in the creation of multimodal 3D forms, central to architectural concept design stages. Presented here are three methodologies of generation of meaningful 2D and 3D designs, merging text-to-image diffusion models Stable Diffusion, and DALL-E 2 with computational methods. These allow designers to intuitively navigate through a multimodal feedback loop of information originating from language and aided by artificial intelligence tools. This paper contributes to our understanding of machine-augmented design processes and the importance of intuitive user interfaces (UI) in enabling new dialogues between humans and machines. Through the creation of a prototype of an accessible UI, this exchange of information can empower designers, build trust in these tools, and increase control over the design process.
keywords	Machine Learning, Diffusion Models, Concept Design, Semantics, User Interface, Design Agency
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	acadia23_v2_420
id	acadia23_v2_420
authors	Guida, George; Escobar, Daniel; Navarro, Carlos
year	2023
title	3D Neural Synthesis: Gaining Control with Neural Radiance Fields
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-0-3]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 420-428.
summary	This research introduces a novel, 3D machine-learning, aided design approach for early design stages. Integrating language within a multimodal framework grants designers greater control and agency in generating 3D forms. The proposed method leverages Stable Diffusion and Runway's Gen1 through the generation of 3D Neural Radiance Fields (NeRFs), surpassing the limitations of 2D image-based outcomes in aiding the design process. This paper presents a flexible machine-learning workflow taught to students in a conference workshop, and outlines the multimodal methods used - between text, image, video, and NeRFs. The resultant NeRF design outcomes are contextualized within a Unity agent-based, virtual environment for architectural simulation, and are expe- rienced with real-time VFX augmentations. This hybridized design process ultimately highlights the importance of feedback loops and control within machine-learning, aided-design processes.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:12

_id	cdrf2023_24
id	cdrf2023_24
authors	Haoran Ma, Hao Zheng
year	2023
title	Text Semantics to Image Generation: A Method of Building Facades Design Base on Stable Diffusion Model
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_3
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
summary	Stable Diffusion model has been extensively employed in the study of architectural image generation, but there is still an opportunity to enhance in terms of the controllability of the generated image content. A multi-network combined text-to-building facade image generating method is proposed in this work. We first fine-tuned the Stable Diffusion model on the CMP Facades dataset using the LoRA (Low-Rank Adaptation) approach, then we apply the ControlNet model to further control the output. Finally, we contrasted the facade generating outcomes under various architectural style text contents and control strategies. The results demonstrate that the LoRA training approach significantly decreases the possibility of fine-tuning the Stable Diffusion large model, and the addition of the ControlNet model increases the controllability of the creation of text to building facade images. This provides a foundation for subsequent studies on the generation of architectural images.
series	cdrf
email
last changed	2024/05/29 14:04

_id	sigradi2023_179
id	sigradi2023_179
authors	He, Mingyi, Su, Zixin, Xie, Yantong and Tu, Han
year	2023
title	Linguistic Landscape Research on the Relationship of Urban Language and Commerce Based on Large-scale Street View Images
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 1737–1748
summary	Urban linguistic landscape studies examine visible written languages in urban areas, revealing socio-economic information, such as the place identity of minority groups and the localization processes of exotic language varieties. However, studies mainly utilize qualitative analysis or small-scale image acquisition without integrating socioeconomic quantitative analysis. Our research aims to expand the quantitative indicators of linguistic landscape in city-wide scale to explore the relationship between detailed quantitative text analysis and consumer prices in spatially differentiated and temporally controlled urban street view images. We examine such correlation through street view images scrapping of historical Baidu Street View images, semantic segmentation machine learning tools, and Optical Character Recognition. Our study reveals a negative correlation between linguistic landscape indicators in street signage and consumption levels. This research provides quantitative methods for large-scale and repeatable study of linguistic landscape, introducing a novel perspective on linguistic landscape evidence for further urban economic development and urban segmentation.
keywords	Cultural landscapes and new technologies, Linguistic landscape, Machine learning, Urban economy, Street view
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	sigradi2023_114
id	sigradi2023_114
authors	Huang, Sheng-Yang, Wang, Yuankai and Jiang, Qingrui
year	2023
title	(In)Visible Cities: Exploring generative artificial intelligence'screativity through the analysis of a conscious journey in latent space
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 717–728
summary	The rise of generative AI has redefined architectural design by introducing latent space, challenging traditional methods. This paper aims to explore, structure, and analyse latent journeys, drawing from analytical design discourses. We construct journeys towards 'Isaura' from 'Invisible Cities' by Italo Calvino, bridging literature and visual narratives, utilising the text-image generating software, Midjourney. The objective is to identify spatial configurations that align with the designer's interpretation of the text, ensuring the accuracy of visual elements. Structured as a Markov (stochastic) process, the experiment encompasses four primary stages to offer a rational explanation for the journey and the role of each segment. Findings emphasise the potential of latent space in augmenting architectural design and underscore the necessity for analytical tools to avert the reduction of design to trivial formalism. The study's outcome suggests that understanding and leveraging the traits of latent space can nurture a more meaningful engagement with AI-driven design, presenting a novel approach to architectural creativity.
keywords	Latent Space, Generative Artificial Intelligence, Text-to-image Generation, Architectural Creativity, Spatial Analysis
series	SIGraDi
email
last changed	2024/03/08 14:07

For more results click below: