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 797

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

_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	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	ascaad2023_134
id	ascaad2023_134
authors	Salman, Huda; Dounas, Theodoros; Clarke, Connor
year	2023
title	Fluency of Creative Ideas in the Digital Age: Exploring Emergent AI Influences on Design Methodology and Visual Thinking in Architectural Education
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. 815-832.
summary	Research has explored the concept of originality in visual thinking and architectural education, using different methods. The new state of Artificial Intelligence (AI) in architectural design represents another shift from traditional modes of architectural design and education, into a more authentic approach to the digital age. An experiment is designed to highlight the originality of this approach in design thinking and its futuristic trends and impact on education and creativity studies. The intent of the study we present here is twofold: one to revisit key design studies of design exploration and secondly to explore students' design activity while interacting with text-to-image diffusion machine learning (ML) generative models such as Midjourney, DALL-E and Stable Diffusion, as these might have the potential to change the way that architectural students approach the concept stages of designing projects and products. In addition, we are interested in how the new shift in interfaces and modes of stimulus will influence the students' design process and perceptions. Participants in the design process are final year students who had spent at least four years in a school of architecture and can be classified as semi-experienced designers. Further within the evaluation also lies a critique of the diffusion ML tools themselves as producers of architectonic images, rather than complete concepts for architecture that encapsulate spatial, formal, structural arrangements of elements.
series	ASCAAD
email
last changed	2024/02/13 14:41

_id	acadia23_v2_582
id	acadia23_v2_582
authors	Wu, Kaicong; Li, Chenming; Su, Wenjun
year	2023
title	The Chair Game Experiment: Transforming Multiplayer Design Processes with Text-to-Image Generation and 2D-to-3D Modelling
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 582-595.
summary	The urgency for an inclusive architectural design process in conceptualizing the built environment stems from the need to establish effective communication between under- represented groups and design professionals. However, various challenges hinder the development of an inclusive design process that accommodates diverse stakeholders. Individual designers or selective design teams are frequently limited by their own visions, causing them to potentially overlook alternative solutions. Moreover, stakeholders who lack professional training might struggle to articulate their expectations. The emergence of generative AI (artificial intelligence) technologies has significantly reduced the tech- nical barriers in design, and has empowered non-professionals to vividly express their ideas regarding forms and spaces. This has presented a valuable opportunity to better understand the perspectives of underrepresented groups through visual representations. Therefore, this research aims to explore the impact of image generation on the democ- ratization of the design process. Using chair design as a testing ground, we propose an evolutionary computing framework that simulates interactions among designers and participants empowered by emerging AI technologies. To investigate the potential impact of image generation, we have implemented a multiplayer design game to allow computing agents to compete in exploring 3D chair forms. Through this approach, we aim to gain insights into how image generation influences design decisions, whether it generates more diversified solutions, and what values could be introduced into the built environment.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:13

_id	ascaad2023_075
id	ascaad2023_075
authors	Aljhadali, Abdulrahman; Megahed, Yasser; Gwilliam, Julie
year	2023
title	Artificial Intelligence (AI) and Machine Learning (ML) in Practice: A Comprehensive Investigation into the Utilization of Generative Artificial Intelligence (AI) and Machine Learning (ML) in Architectural Practice
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. 324-343.
summary	This study offers a comprehensive investigation into the utilization of artificial intelligence (AI) and machine learning (ML) technologies within architectural practices. Since the introduction of computer-aided design (CAD), technology has had a significant impact on the way architects conduct their work. This study explores the potential of AI/ML in actual architectural workflows, with a particular emphasis on the capacity of deep neural networks to assist in the design process.The outcome will help to develop a clearer picture of the opportunities and barriers associated with AI for architects; they will also inform the prioritization of focus for future development of this technology in architectural practice, as well as identifying the specific tasks and project phases in which ML could play a role. This research reviewed literature to explore various approaches for applying AI/ML technologies within the field of architecture. Also , complemented by a number of interviews to investigate the ways in which participants are currently using AI/ML in their work, framing the current feedback and the future potential of AI/ML technologies in architecture. The data collection methods adopted involved semi-structured one-on-one interviews with professionals from multi-regional architecture firms and AI developers. The architects interviewed exhibited diverse ways of benefiting from AI/ML technology, with varying approaches and some common trends. The findings demonstrate that AI has played a pivotal role in expediting the design process and enhancing visualization within the field. However, it has also raised concerns, particularly in the realm of privacy.
series	ASCAAD
email
last changed	2024/02/13 14:40

_id	ecaade2023_125
id	ecaade2023_125
authors	Baºarir, Lale, Çiçek, Selen and Koç, Mustafa
year	2023
title	Demystifying the patterns of local knowledge: The implicit relation of local music and vernacular architecture
doi	https://doi.org/10.52842/conf.ecaade.2023.2.791
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. 791–800
summary	As the zeitgeist suggests, the development of novel design output using Artificial Neural Networks (ANNs) is becoming an important milestone in the architectural design discourse. With the recent encounter of the computational design realm with the diffusion models, it becomes even easier to generate 2D and 3D design outputs. Yet, the utilization of machine learning tools within design computing domains is confined to generating or classifying visual and encoded data. However, it is critical to evaluate the untapped potentials of machine learning technologies in terms of illuminating the implicit correlations and links underlying distinct concepts and themes across a wide range of technical domains. With the ongoing research project named “Local Intelligence", we hypothesized that the local knowledge of a certain location might be conceptualized as a distributed network to connect different forms of local knowledge. As the first case of the project, we tried to reinstate a commonality between the local music and vernacular architecture, for which we trained generative adversarial network (GAN) models with the visual spectrograms translated from the audio data of the local songs and images of vernacular architectural instances from a defined geography. The two multi-modal GAN models differ in terms of the inherent convolutional layers and data pairing process. The outcomes demonstrated that both GAN models can learn how to depict vernacular architectural features from the rhythmic pattern of the songs in various patterns. Consequently, the implicit relations between music and architecture in the initial findings come one step closer to being demystified. Thus, the process and generative outcomes of the two models are compared and discussed in terms of the legibility of the architectural features, by taking the original vernacular architectural image dataset as the ground truth.
keywords	Local Intelligence, Machine Learning, Generative Adversarial Network (GAN), Local Music, Vernacular Architecture
series	eCAADe
email
last changed	2023/12/10 10:49

_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	sigradi2023_439
id	sigradi2023_439
authors	Chornobai, Sara Regiane, Paiva Ponzio, Angelica, Miotto Bruscato, Léia and Machado Fagundes, Cristian Vinicius
year	2023
title	Fostering Sustainability in the Early Stages of the Architectural Design process: a Creative Exploration of AI Generative Models
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. 831–842
summary	The field of architecture is experiencing transformative changes with the rise of Artificial Intelligence (AI). This study investigates the use of generative models like Large Language Models (LLM) and Generative Diffusion Models (GDM) in architectural design, focusing on sustainability. Utilizing the concept of “active human agency”, the research evaluates tools like DALL-E 2 (Bing) and ChatGPT (GPT-4) for creating environmentally responsive references in the early phases of the design process. Employing an explorative and qualitative methodology, the investigation includes architectural characteristics of climatic archetypes and concepts related to architecture-biology, applied to different environmental contexts. Initial findings reveal the AI potential in creating environmentally responsive references, with certain limitations in specific interactions and interpretations. The conclusion emphasizes these tools as collaborative aids in early design stages, and underscores the importance of "active human agency" for meaningful, responsible results, contributing to sustainability in early architectural design processes.
keywords	Artificial Intelligence, Generative Models, Architectural Design Process, Sustainability, Active Human Agency.
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	sigradi2023_469
id	sigradi2023_469
authors	Fernandez Gonzalez, Alberto and Bognar, Melinda
year	2023
title	Exploring the Evolution of Digital Detail in Architecture: From Pixels and Voxels to AI- Enhanced Design Techniques
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. 1773–1784
summary	This paper explores the significant evolution of digital architecture, tracing its development from the introduction of basic elements like pixels and vectors to the sophisticated integration of AI and stable diffusion models. Beginning with the shift from manual sketching to computer-aided design (CAD), the paper examines how these foundational components have enabled more precise and intricate designs. The incorporation of AI has further transformed the field, allowing for advanced techniques such as generative design and performance optimization. Additionally, the research emphasizes the role of stable diffusion models in maximizing design performance and translating 2D data into 3D spaces. The paper also considers the broader impact of these technologies on the industry, leading to innovative paradigms like biomimicry and smart cities. Overall, the paper provides a comprehensive overview of digital architecture's transformative potential and its role in shaping a more innovative and equitable built environment.
keywords	Artificial Intelligence, Neural Networks, GANs, Stable Diffusion, Detail
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	acadia23_v2_72
id	acadia23_v2_72
authors	Hosmer, Tyson; Mutis, Sergio; Hughes, Eric; He, Ziming; Siedler, Philipp; Gheorghiu, Octavian; Erdinçer, Bariº
year	2023
title	Autonomous Collaborative: Robotic Reconfiguration with Deep Multi-Agent Reinforcement Learning (ACRR+DMARL)
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 72-90.
summary	To address the unprecedented challenges of the global climate and housing crises, requires a radical change in the way we conceive, plan, and construct buildings, from static continuous objects to adaptive eco-systems of reconfigurable parts. Living systems in nature demonstrate extraordinary scalable efficiencies in adaptive construction with simple flexible parts made from sustainable materials. The interdisciplinary field of collec- tive robotic construction (CRC) inspired by natural builders has begun to demonstrate potential for scalable, adaptive, resilient, and low-cost solutions for building construc- tion with simple robots. Yet, to explore the opportunities inspired by natural systems, CRC systems must be developed utilizing artificial intelligence for collaborative and adaptive construction, which has yet to be explored. Autonomous Collaborative Robotic Reconfiguration (ACRR) is a robotic material system with an adaptive lifecycle trained with deep, multi-agent reinforcement learning (DMARL) for collaborative reconfigura- tion. Autonomous Collaborative Robotic Reconfiguration is implemented through three interrelated components codesigned in relation to each other: 1) a reconfigurable robotic material system; 2) a cyber-physical simulation, sensing, and control system; and 3) a framework for collaborative robotic intelligence with DMARL. The integration of the CRC system with bidirectional cyber-physical control and collaborative intelligence enables ACRR to operate as a scalable and adaptive architectural eco-system. It has the potential not only to transform how we design and build architecture, but to fundamentally change our relationship to the built environment moving from automated toward autonomous construction.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:12

_id	ecaade2023_387
id	ecaade2023_387
authors	Huang, Sheng-Yang, Llabres-Valls, Enriqueta, Tabony, Aiman and Castillo, Luis Carlos
year	2023
title	Damascus House: Exploring the connectionist embodiment of the Islamic environmental intelligence by design
doi	https://doi.org/10.52842/conf.ecaade.2023.2.871
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. 871–880
summary	Past studies have demonstrated that connectionist artificial intelligence (AI) has superior capabilities for style-based generative design because it automatically searches, extracts, and applies features according to the data-represented probabilistic profile of an architectural style. To further navigate its architectural affordance, this practice-led research project explores employing connectionist artificial intelligence to produce Islamic-style architectural forms that have historically revealed environmental intelligence by embedding sociocultural factors in response to the physical and human environmental design heritage. The project applies the Pix2Pix model and inverts the logic of some existing studies to predict the building plans from daylight maps. Use multi-objective optimisation algorithms to iteratively optimise factors such as building porosity, spatial quality, and microclimate, and use it as a condition to apply a Pix2Pix to generate a corresponding porosity model that is parametrised for the further design process. The model was trained on 120 augmented, paired images based on the 30 selected examples of Islamic architecture from the Damascus Atlas to capture the relationship between the massing distribution of walls and the arrangement of major elements in an Islamic courtyard house and its thermal performance. This study seeks to test if connectionist AI can be used as a generative design tool to understand the historical development of spatial relationships in Islamic courtyard houses. It focuses on non-repetitive style metrics, embedding physical and cultural factors into data representation. The resulting environmentally intelligent model adapts to the context, with optimisation being a pragmatic design guide rather than the ultimate goal. Although the inference is based on objective probabilistic facts, the influence of the informational framework interpreted by the designers must be acknowledged.
keywords	Connectionist Artificial Intelligence, Digital Design, Environmental Intelligence, Islamic Architecture, Style-based Generative Design
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2023_416
id	sigradi2023_416
authors	Machado Fagundes, Cristian Vinicius, Miotto Bruscato, Léia, Paiva Ponzio, Angelica and Chornobai, Sara Regiane
year	2023
title	Parametric environment for internalization and classification of models generated by the Shap-E tool
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. 1689–1698
summary	Computing has been increasingly employed in design environments, primarily to perform calculations and logical decisions faster than humans could, enabling tasks that would be impossible or too time-consuming to execute manually. Various studies highlight the use of digital tools and technologies in diverse methods, such as parametric modeling and evolutionary algorithms, for exploring and optimizing alternatives in architecture, design, and engineering (Martino, 2015; Fagundes, 2019). Currently, there is a growing emergence of intelligent models that increasingly integrate computers into the design process. Demonstrating great potential for initial ideation, artificial intelligence (AI) models like Shap-E (Nichol et al., 2023) by OpenAI stand out. Although this model falls short of state-of-the-art sample quality, it is among the most efficient orders of magnitude for generating three-dimensional models through AI interfaces, offering practical balance for certain use cases. Thus, aiming to explore this gap, the presented study proposes an innovative design agency framework by employing Shap-E connected with parametric modeling in the design process. The generation tool has shown promising results; through generations of synthetic views conditioned by text captions, its final output is a mesh. However, due to the lack of topological information in models generated by Shap-E, we propose to fill this gap by transferring data to a parametric three-dimensional surface modeling environment. Consequently, this interaction's use aims to enable the transformation of the mesh into quantifiable surfaces, subject to collection and optimization of dimensional data of objects. Moreover, this work seeks to enable the creation of artificial databases through formal categorization of parameterized outputs using the K-means algorithm. For this purpose, the study methodologically orients itself in a four-step exploratory experimental process: (1) creation of models generated by Shap-E in a pressing manner; (2) use of parametric modeling to internalize models into the Grasshopper environment; (3) generation of optimized alternatives using the evolutionary algorithm (Biomorpher); (4) and classification of models using the K-means algorithm. Thus, the presented study proposes, through an environment of internalization and classification of models generated by the Shap-E tool, to contribute to the construction of a new design agency methodology in the decision-making process of design. So far, this research has resulted in the generation and classification of a diverse set of three-dimensional shapes. These shapes are grouped for potential applications in machine learning, in addition to providing insights for the refinement and detailed exploration of forms.
keywords	Shap-E, Parametric Design, Evolutionary Algorithm, Synthetic Database, Artificial Intelligence
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	ecaade2023_44
id	ecaade2023_44
authors	Mayrhofer-Hufnagl, Ingrid and Ennemoser, Benjamin
year	2023
title	From Linear to Manifold Interpolation: Exemplifying the paradigm shift through interpolation
doi	https://doi.org/10.52842/conf.ecaade.2023.2.419
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. 419–429
summary	The advent of artificial intelligence, specifically neural networks, has marked a significant turning point in the field of computation. During such transformative times, we are often faced with a dearth of appropriate vocabulary, which forces us to rely on existing terms, regardless of their inadequacy. This paper argues that the term “interpolation,” typically used in deep learning (DL), is a prime example of this phenomenon. It is not uncommon for beginners to misunderstand its meaning, as DL pioneer Francois Chollet (2017) has noted. This misreading is especially true in the discipline of architecture, and this study aims to demonstrate how the meaning of “interpolation” has evolved in the second digital turn. We begin by illustrating, using 2D data, the difference between linear interpolation in the context of topological figures and its use in DL algorithms. We then demonstrate how 3DGANs can be employed to interpolate across different topologies in complex 3D space, highlighting the distinction between linear and manifold interpolation. In both 2D and 3D examples, our results indicate that the process does not involve continuous morphing but instead resembles the piecing together of a jigsaw puzzle to form many parts of a larger ambient space. Our study reveals how previous architectural research on DL has employed the term “interpolation” without clarifying the crucial differences from its use in the first digital turn. We demonstrate the new possibilities that manifold interpolation offers for architecture, which extend well beyond parametric variations of the same topology.
keywords	Interpolation, 3D Generative Adversarial Networks, Deep Learning, Hybrid Space
series	eCAADe
email
last changed	2023/12/10 10:49

_id	cdrf2023_368
id	cdrf2023_368
authors	Peter Buš
year	2023
title	DeepCraft: Co-Intelligent Architecture and Human and AI-Driven Craftsmanship in Design-to-Production Pipelines
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_31
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
summary	The working paper investigates the potential of artificial intelligence technologies (AI), namely the Generative Adversarial Imitation Learning (GAIL) implemented in a process of digital robotic fabrication prospectively to be used in craftsmanship. The method introduced is based on a preliminary demonstration provided digitally in an abstract toolpath generated by a human-driven movement in a hand gesture translated into a digital space in a real-time process. The investigation presented in this paper focuses on a preliminary computational digital framework which may serve as a base for further investigation. At this stage of the report, the framework encompasses human hand recognition creating a toolpath for a robot, which learns its principles and tries to interpret the process in a digital space. This learned toolpath resulted in a digital brain being applied again in a different shape of the human-created toolpath or gesture movement. The paper also presents the computational system of the real-time navigation of the robot based on a human gesture in a virtual space. The learned knowledge by a robot is observed in a digital environment before any physical applications.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2023_470
id	ecaade2023_470
authors	Sharafi Rohani, Nima and Akçay Kavakoglu, Ayºegül
year	2023
title	AI-Driven Spatial Adaptations Through Emotions: The case of emo-land as a human-centric approach
doi	https://doi.org/10.52842/conf.ecaade.2023.2.889
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. 889–898
summary	The research on controlling and interacting with the environment has been accelerated by developments of artificial intelligence (AI) and the internet of things (IoT). While the quest for intelligence has been widely studied, spatial adaptation and human emotion relation remain ambiguous. This initial research attempts to investigate human-centric spatial adaptations through emotions in architecture. A case study called Emo-Land is designed to unfold the real-time relationship between space and emotion recognition. Emo-Land is an interactive spatial augmented reality installation that responds to the real-time emotions of the viewer via face expressions. A deep learning model developed to detect continuous emotions through cameras. By paying attention to the live interactive level of the detail and quality of the interaction between users and the projection mapping, the research demonstrates how advances in technology and computing can contribute to deeper connection and new layers of interactivity. Emo-Land projection mapping has been examined as a case study. According to the results, a relationship is developed between emotion recognition, form, computation, and human-computer interaction. The project contributes to the well-being of occupants, affective computing theory, and AI's role, such as the interaction between technology using affordable technologies.
keywords	Artificial Intelligence, Emotion Recognition, Affective Computing, Spatial Adaptation, Human-Centric Environments, Interactive Design
series	eCAADe
email
last changed	2023/12/10 10:49

_id	acadia23_v2_430
id	acadia23_v2_430
authors	Vaidhyanathan, Vishal; T R, Radhakrishnan; Garcia del Castillo Lopez, Jose Luis
year	2023
title	Spacify: A Generative Framework for Spatial Comprehension, Articulation and Visualization using Large Language Models (LLMs) and eXtended Reality (XR)
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 430-443.
summary	Spatial design, the thoughtful planning and creation of built environments, typically requires advanced technical knowledge and visuospatial skills, making it largely exclusive to professionals like architects, interior designers, and urban designers. This exclusivity limits non-experts' access to spatial design, despite their ability to describe requirements and suggestions in natural language. Recent advancements in generative artificial intelligence (AI), particularly large language models (LLMs), and extended reality, (XR) offer the potential to address this limitation. This paper introduces Spacify (Figure 1), a framework that utilizes the generalizing capabilities of LLMs, 3D data-processing, and XR interfaces to create an immersive medium for language-driven spatial understanding, design, and visualization for non-experts. This paper describes the five components of Spacify: External Data, User Input, Spatial Interface, Large Language Model, and Current Spatial Design; which enable the use of generative AI models in a) question/ answering about 3D spaces with reasoning, b) (re)generating 3D spatial designs with natural language prompts, and c) visualizing designed 3D spaces with natural language descriptions. An implementation of Spacify is demonstrated via an XR smartphone application, allowing for an end-to-end, language-driven interior design process. User survey results from non-experts redesigning their spaces in 3D using this application suggest that Spacify can make spatial design accessible using natural language prompts, thereby pioneering a new realm of spatial design that is naturally language-driven.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:12

_id	ecaade2023_161
id	ecaade2023_161
authors	Wang, Xiaolu
year	2023
title	Photogrammetry Enables the Critical Reinterpretation and Regeneration of Architectural Heritage
doi	https://doi.org/10.52842/conf.ecaade.2023.2.661
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. 661–670
summary	Photogrammetry is a digital technique that uses 2D images to create 3D models, which has various applications in cultural heritage such as documentation, digital tourism, and restoration, which mainly focus on current and future needs. However, there is limited literature regarding on how photogrammetry can be used for better research of architectural history. Photogrammetry is a potential tool to obtain a comprehensive exploration of the past. A more comprehensive exploration of the past will certainly have an impact on the sustainable regeneration of architectural heritage. Therefore, this paper aims to bring forward digital application as a research method of historical interpretation by using photogrammetry. The research implemented the photogrammetric method to investigate the site of ‘UNESCO Foguang Monastery’ in China by collecting aerial photographs using drone, then employed Reality Capture software to create a 3D model of the mountain monastery. Through this 3D model of the monastery and its vicinity, the artificial gullies around the enclosed courtyard, as a part of religious landscape, were discovered for the first time by the author. This discovery promotes the understanding of religious landscape history because the gullies create land boundaries and define the sacred place that presents Buddhist cosmology. This finding indicates that in transforming a common land into a sacred site, Buddhists not only erected monastic monuments, but also considered the religious landscape. This study also aims to inspire historical architecture researchers to employ digital methods and broaden their perspective on surveying architectural heritage, particularly in relation to their landscape scale.
keywords	Architectural heritage, photogrammetric technology, Reality Capture, architectural history, religious landscape, Foguang Monastery
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2023_356
id	sigradi2023_356
authors	Wojcickoski, Vagner and Osterkamp, Guilherme
year	2023
title	Application of the “Double-Layered Model” Concept for the Use of AI in the Atelier
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. 1477–1488
summary	The objective of this article is to present the application of the "Double-Layered Model" concept for image generation using AI tools in a design studio. To delimit this study, a workshop was conducted in a controlled environment, along with utilizing control protocols and analyzing the results produced in an undergraduate Architecture course in Brazil. The discipline challenges students to develop an urban park with the aim of illustrating future realities. The analysis of the process and the generated results allowed for an evaluation of the potential for generating images through an AI system, in light of concepts described by Goldschmidt. The students were guided to create images using inputs related to the concept. The variability of results based on the propositions for the design problem, combined with the guidance provided by the applied concept, suggests a potential supportive tool for generating ideas in a design studio.
keywords	Artificial Intelligence, Text-to-Image Generator, Landscape, Design Studio, Double-Layered Model.
series	SIGraDi
email
last changed	2024/03/08 14:08

_id	ascaad2023_055
id	ascaad2023_055
authors	Yildiz, Berfin; Çagdaº, Gülen; Zincir, lbrahim
year	2023
title	Deep Architectural Floor Plan Generation: An Approach for Open-Planned Residential Spaces
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. 685-705.
summary	This research investigates the collaborative potential of artificial intelligence and deep learning in architectural design, focusing on comprehending and synthesizing the complex relationships within architectural floor plans. The primary question addressed is whether deep learning algorithms can effectively generate residential floor plans characterized by open-planned architectural spaces. To address this, the study introduces a novel model employing generative adversarial networks (GANs) to create open-planned layouts within residential floor plans. Open-planned spaces refers to a design approach in which interior spaces within a structure are intentionally devoid of traditional partitioning elements such as walls and doors. The layout typically features interconnected and visually continuous spaces that flow seamlessly from one area to another. The research contributes by addressing a gap in the literature through the exploration of functional space differentiations within residences characterized by open plan arrangement without walls as a separating element. Furthermore, the study extends this investigation by applying the proposed methodology to angular and circular plans as well as orthogonal plan sets. In the generative model created with GAN, the space functions are defined and labelled with the RGB color codes assigned to them. For the RGB label representation of the open-plan layout, gradient coloring prepared. By using this method, it was investigated whether the generation of the plans was realized with an open-plan structure by examining the gradient generation results. In the generative model, the footprint of the plan is given as an input for the algorithm to produce by adhering to an outer boundary. Accordingly, it is aimed to learn how the network can be arranged within the given boundaries. The Pix2pix method was used for this generative model, which is defined as the problem of obtaining images from images. The model results advance the AI-driven understanding of architectural design by providing architects with an innovative tool to explore open-plan spatial solutions.
series	ASCAAD
email
last changed	2024/02/13 14:34

For more results click below: