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 579

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

_id	ecaade2022_270
id	ecaade2022_270
authors	Akcay Kavakoglu, Aysegul, Almac, Bihter, Eser, Begum and Alacam, Sema
year	2022
title	AI Driven Creativity in Early Design Education - A pedagogical approach in the age of Industry 5.0
doi	https://doi.org/10.52842/conf.ecaade.2022.1.133
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 133–142
summary	This study presents a pedagogical experiment on the integration of AI into the project studio in the early stages of design education. The motivation of the study is to support creative encounters in design studios by promoting student-design representation, student-student, and student-artificial intelligence (AI) interaction. In the scope of this study, a short-term studio project is used as a case study to examine these creative encounters. The experiment covers five stages that enable a recursive analysis-synthesis action. The stages include (i) precedent analysis of a given set of building façades images, (ii) feature extraction, (iii) composing new façade representations through employing previously generated features, (iv) training an AI by the use of styleGAN2-ADA with the outcomes of stage 3, (v) Use of synthetically generated façade images as a design driver. The pedagogical experiment is evaluated through the lenses of novelty, style, surprisingness, and complexity concepts. The challenges and potentials are introduced, as well as elaborations on the future directions of the interplay between AI-oriented making and first-year student making.
keywords	Artificial Intelligence, Computational Creativity, Design Education, StyleGAN2-ADA
series	eCAADe
email
last changed	2024/04/22 07:10

_id	acadia22pr_82
id	acadia22pr_82
authors	Esquivel, Gabriel; Jaminet, Jean; Bugni, Shane
year	2022
title	The Serlio Code - Beyond Classic Language
source	ACADIA 2022: Hybrids and Haecceities [Projects Catalog of the 42nd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-7-4]. University of Pennsylvania Stuart Weitzman School of Design. 27-29 October 2022. edited by M. Akbarzadeh, D. Aviv, H. Jamelle, and R. Stuart-Smith. 82-87.
summary	This research project examined the illustrated expositions of Sebastiano Serlio through the lens of artificial intelligence. The intention of this project was to use Serlio’s illustrations to modulate their qualities and problematize their 2D to 3D translation beyond the rules of representation and orthographic projection. Three operative models were presented: columns, plans and facades, and porticoes—developed by augmenting and interpreting layered generative adversarial networks that drive an integrated parametric 3D process. These insights and investigations disclosed alternative theoretical connections between information processing and aesthetic communication as well as emerging modes of creative digital production.
series	ACADIA
type	project
email
last changed	2024/02/06 14:06

_id	acadia22_742
id	acadia22_742
authors	Leach, Neil
year	2022
title	What is Creativity?
source	ACADIA 2022: Hybrids and Haecceities [Proceedings of the 42nd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-8-1]. University of Pennsylvania Stuart Weitzman School of Design. 27-29 October 2022. edited by M. Akbarzadeh, D. Aviv, H. Jamelle, and R. Stuart-Smith. 742-751.
summary	This paper explores what we can perhaps begin to understand about the nature of creativity in the mirror of AI, with reference to the now famous Go match between AlphaGo and Lee Sedol. It argues that one particular famous move in that match sheds light on some of the crucial questions regarding creativity. It compares this move to the ‘smart’ architectural designs generated by AI, and asks whether computers can be creative, or whether they are simply conducting a ‘search and synthesis’ operation. Finally, the paper asks the provocative question, as to whether creativity even exists, or whether it is a myth that can now be debunked, thanks to our insights from the world of AI.
series	ACADIA
type	paper
email
last changed	2024/02/06 14:04

_id	acadia22pr_52
id	acadia22pr_52
authors	Rieger, Uwe; Liu, Yinan; Kaluarachchi, Tharindu; Barde, Amit
year	2022
title	LightSense - Architecture as a Creative Partner
source	ACADIA 2022: Hybrids and Haecceities [Projects Catalog of the 42nd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-7-4]. University of Pennsylvania Stuart Weitzman School of Design. 27-29 October 2022. edited by M. Akbarzadeh, D. Aviv, H. Jamelle, and R. Stuart-Smith. 52-57.
summary	LightSense is an interactive Extended Reality (XR) installation. It is a design research project that investigates a new generation of responsive architecture by linking a transformable physical construction with its Artificial Intelligence (AI) enhanced digital twin.
series	ACADIA
type	project
email
last changed	2024/02/06 14:04

_id	caadria2022_508
id	caadria2022_508
authors	Yousif, Shermeen and Bolojan, Daniel
year	2022
title	Deep Learning-Based Surrogate Modeling for Performance-Driven Generative Design Systems
doi	https://doi.org/10.52842/conf.caadria.2022.1.363
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 363-372
summary	Within the context of recent research to augment the design process with artificial intelligence (AI), this work contributes by introducing a new method. The proposed method automates the design environmental performance evaluation by developing a deep learning-based surrogate model to inform the early design stages. The project is aimed at automating performative design aspects, enabling designers to focus on creative design space exploration while retrieving real-time predictions of environmental metrics of evolving design options in generative systems. This shift from a simulation-based to a prediction-based approach liberates designers from having to conduct simulation and optimization procedures and allows for their native design abilities to be augmented. When introduced into design systems, AI strategies can improve existing protocols, and enable attaining environmentally conscious designs and achieve UN Sustainable Development Goal 11.
keywords	Deep Learning, Artificial Intelligence, Surrogate Modeling, Automating Building Performance Simulation, Generative Design Systems, SDG11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_65
id	ecaade2022_65
authors	Halici, Süheyla Müge and Gül, Leman Figen
year	2022
title	Utilizing Generative Adversarial Networks for Augmenting Architectural Massing Studies: AI-assisted Mixed Reality
doi	https://doi.org/10.52842/conf.ecaade.2022.1.323
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 323–330
summary	A technique for architectural massing studies in Mixed Reality (MR) is described. Generative Adversarial Networks let an object appear to have a different material than it actually has. The benefits during design are twofold. From one side the congruence between shape and material are subject to verification in real-time. From the other side, the designer is liberated from the usual restrictions and biases as to shape that are inevitable due to the mechanical properties of a mock-up. This is referred to as artificial intelligence assisted MR (AI-A MR) in this work. The technique consists of two steps: based on preparing synthetic data in Rhino/Grasshopper to be trained with an image-to- image translation model and implemented to the trained model in MR design environment. Next to the practical merits, a contribution of the work with respect to MR methodology is that it exemplifies the solution of some persistent tracking and registration problems.
keywords	Hybrid Design Environment, Dynamic Design Models, Mixed Reality, Generative Adversarial Networks, Image-to-Image Translation, Tracking
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_234
id	ecaade2022_234
authors	Afsar, Secil, Estévez, Alberto T., Abdallah, Yomna K., Turhan, Gozde Damla, Ozel, Berfin and Doyuran, Aslihan
year	2022
title	Activating Co-Creation Methodologies of 3D Printing with Biocomposites Developed from Local Organic Wastes
doi	https://doi.org/10.52842/conf.ecaade.2022.1.215
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 215–224
summary	Compared to the take-make-waste-oriented linear economy model, the circular model has been studied since the 1980s. Due to consumption-oriented lifestyles along with having a tendency of considering waste materials as trash, studies on sustainable materials management (SMM) have remained at a theoretical level or created temporary and limited impacts. To ensure SMM supports The European Green Deal, there is a necessity of developing top-down and bottom-up strategies simultaneously, which can be metaphorized as digging a tunnel from two different directions to meet in the middle of a mountain. In parallel with the New European Bauhaus concept, this research aims to create a case study for boosting bottom-up and data-driven methodologies to produce short-loop products made of bio-based biocomposite materials from local food & organic wastes. The Architecture departments of two universities from different countries collaborated to practice these design democratization methodologies using data transfer paths. The 3D printable models, firmware code, and detailed explanation of working with a customized 3D printer paste extruder were shared using online tools. Accordingly, the bio-based biocomposite recipe from eggshell, xanthan gum, and citric acid, which can be provided from local shops, food & organic wastes, was investigated concurrently to enhance its printability feature for generating interior design elements such as a vase or vertical gardening unit. While sharing each step from open-source platforms with adding snapshots and videos allows further development between two universities, it also makes room for other researchers/makers/designers to replicate the process/product. By combining modern manufacturing and traditional crafting methods with materials produced with DIY techniques from local resources, and using global data transfer platforms to transfer data instead of products themselves, this research seeks to unlock the value of co-creative design practices for SMM.
keywords	Sustainable Materials Management, Co-Creation, Food Waste, 3D Printing, New European Bauhaus
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ascaad2022_013
id	ascaad2022_013
authors	Al-Suwaidi, Mohammed; Agkathidis, Asterios; Haidar, Adonis; Lombardi, Davide
year	2022
title	Application of Immersive Technologies in the Early Design Stage in Architecture Education: A Systematic Review
source	Hybrid Spaces of the Metaverse - Architecture in the Age of the Metaverse: Opportunities and Potentials [10th ASCAAD Conference Proceedings] Debbieh (Lebanon) [Virtual Conference] 12-13 October 2022, pp. 313-330
summary	This paper reviews existing research on the use of immersive technologies, Virtual Reality in particular, in various stages of the architectural design process. Nine research papers were systematically reviewed and analyzed. They were filtered down by using the keywords: ‘Virtual/Augmented Reality, Architectural Education, Gravity Sketch, Unity and Virtual Environments’ from two main databases that focus on digital and computer-aided design research: Cumulative Index about publications in Computer Aided Architectural Design (CuminCAD) and Elsevier's abstract and citation database (Scopus). The selection of papers was filtered down based on relevant approaches which investigate architectural design, creative thinking and teaching methodology using immersive technologies. Another criterion applied to the filtering process of the research papers is the exploration and integration process of new tools and overlapping external software to aid the existing workflow of the user. Our findings explore the evolution of immersive tools to highlight the advantages and disadvantages of virtual reality-based software and hardware, as a creative development tool in the field of education and practice. This paper also proposes a novel teaching methodology that incorporates immersive technologies in the early design phase of architectural education.
series	ASCAAD
email
last changed	2024/02/16 13:24

_id	ecaade2022_292
id	ecaade2022_292
authors	Baudoux, Gaelle, Calixte, Xaviera and Leclercq, Pierre
year	2022
title	Transition between Architectural Ideation and BIM - Towards a new method through semantic building modeling
doi	https://doi.org/10.52842/conf.ecaade.2022.2.357
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 357–366
summary	Faced with the challenges of the actors' coordination regarding the increasing building complexity, the new digital collective approaches of advanced design raise the problem of the transition between collaborative ideation (first creative moments of deployment of ideas) and the following phases of digital production (including the formalisation of building specifications in BIM models). In response, we aim to develop a digitally instrumented method for moving from conventional architectural graphic documents to the 3D digital models characteristic of BIM. We propose here a detailed formalisation of the ideation-BIM transition problem and a method for managing building information to improve this transition.
keywords	Building Information Modeling, Architectural Ideation, Digital Representation, Media Architecture, Semantic Model
series	eCAADe
email
last changed	2024/04/22 07:10

_id	sigradi2022_246
id	sigradi2022_246
authors	Bustos Lopez, Gabriela; Aguirre, Erwin
year	2022
title	Walking the Line: UX-XR Design Experiment for Ephemeral Installations in Pandemic Times
source	Herrera, PC, Dreifuss-Serrano, C, Gómez, P, Arris-Calderon, LF, Critical Appropriations - Proceedings of the XXVI Conference of the Iberoamerican Society of Digital Graphics (SIGraDi 2022), Universidad Peruana de Ciencias Aplicadas, Lima, 7-11 November 2022 , pp. 699–710
summary	Throughout COVID 19 Pandemic since 2020, it was necessary to generate instructional strategies including digital platforms for creative processes in architecture. This article exposes an experience that integrates pedagogical, operational, and technical dimensions in architecture virtual teaching. A pedagogical methodology was designed and implemented, fusing User Experience (UX) and Extended Reality (XR) during the architectural design process in a virtual experimental studio. The use of UX-XR as a designing-reviewing strategy in architecture, positively impacted the creative experience of both students and reviewers by enriching the perception of the space and interactively simulating the user experience. A friendly, fun, and socially inclusive environment was generated for learning architecture using synthetic media and Multiuser Virtual Environments (MUVEs). The successful results of the students’ projects by phase are shown, revealing the significance of combining UX and XR, incorporating the metaverse as a canvas to review, recreate, interact, and assess architectural designs.
keywords	User Experience (UX), Extended Reality (XR), Multiuser Virtual Environments (MUVE), Virtual Campus, Usability
series	SIGraDi
email
last changed	2023/05/16 16:56

_id	ecaade2022_175
id	ecaade2022_175
authors	Di Carlo, Raffaele, Mittal, Divyae and Vesely, Ondrej
year	2022
title	Generating 3D Building Volumes for a Given Urban Context using Pix2Pix GAN
doi	https://doi.org/10.52842/conf.ecaade.2022.2.287
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 287–295
summary	Our ability to delegate the most intellectually demanding tasks to machines improves with each passing day. Even in the fields of architecture and design, which were previously thought to be exclusive domain of human creativity and flare, we are moving the first steps towards developing models that can capture the patterns, invisible to the naked eye, embedded in the creative process. These patterns reflect ideas and traditions, imprinted in the collective mind over the course of history, that can be improved upon or serve as a cautionary tale for the new generation of designers in their work of designing an equitable, more inclusive future. Generative Adversarial Networks (GANs) give us the opportunity to turn style and design into learnable features that can be used to automatically generate blueprints and layouts. In this study, we attempt to apply this technology to urban design and to the task of generating a building footprint and volume that fits within the surrounding built environment. We do so by developing a Pix2Pix model composed of a ResNet-6 generator and a Patch discriminator, applying it to satellite views of neighborhoods from across the Netherlands, and then turning the resulting 2D generated building footprint into a reusable 3D model. The model is trained using the national cadastral data and TU Delft 3D BAG dataset. The results show that it is possible to predict a building shape compatible in style and height with the surroundings. Although the model can be used for different applications, we use it as an evaluation tool to compare the design alternatives fitting the desired contextual patterns.
keywords	Generative Adversarial Networks, Urban Design, Pix2Pix, Raster Vectorization, 3D Rendering
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_89
id	ecaade2022_89
authors	Di Mascio, Danilo
year	2022
title	An Untold Story of a Creative Community of Level Designers - Designing and sharing imaginary navigable virtual environments with game technologies
doi	https://doi.org/10.52842/conf.ecaade.2022.1.481
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 481–490
summary	The following paper describes and critically reflects on the remarkable production of a creative community of level designers who designed and published 3D game levels (3D real-time virtual navigable environments) during the end of the 1990s and the first decade of the 2000s. During those years, many level designers from several countries created an impressive number and variety of custom levels (user-created content), characterised by imaginary architectures and places informed by narrative elements. This international community was supported by various websites that are no longer available. However, an open-source website, Unreal Archive, constitutes “an initiative to preserve and maintain availability of the rich and vast history of user-created content for the Unreal and Unreal Tournament series of games” (Unreal Archive, 2022). The number of levels available on Unreal Archive exceeds 34,000. For the first time in the architectural research community, this paper aims to shed light on the creative production of that period, and to identify and critically reflect on aspects that could have cultural, creative and educational value for architecture and architectural education. The author directly experienced the achievements of that historical period, and created and published a number of virtual environments using early versions of the Unreal Editor/Engine and 3D modelling software. This research is part of a larger project that investigates transdisciplinary expressions of spaces and architectures, as well as concepts, methodologies and tools in the video games field that can inspire or be transferred to the architecture field.
keywords	Virtual Environments, Imaginary Architectures and Places, Narrative, 3D Navigable Environments, Digital Heritage, User-Created Content, Unreal Editor, Unreal Series, Video Games, Level Design, Environmnetal Storytelling
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_154
id	ecaade2022_154
authors	Ferretti, Maddalena, Di Leo, Benedetta, Quattrini, Ramona and Vasic, Iva
year	2022
title	Creativity and Digital Transition in Central Apennine - Innovative design methods and digital technologies as interactive tools to enable heritage regeneration and community engagement
doi	https://doi.org/10.52842/conf.ecaade.2022.2.187
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 187–196
summary	This contribution proposes strategies of reactivation of the central Apennine of Marche Region in Italy through creative design methods and virtual technologies. The research activities are connected to two related PhD projects: one focusing on architectural and urban design, the other one on heritage digitalization and new technologies and to other research activities of our interdisciplinary team. Cagli, a small town of 8.000 inhabitants, is currently undergoing socio-economic transformations that need to be addressed strategically with a cultural and spatial perspective. The research explores regenerative solutions and local development strategies to enhance the city and its cultural landscape. Participatory processes aided by digital tools and innovative design methods are tested in Cagli’s living lab. The final output of the overall research is a “Reactive Map” combining a trans-scalar and multidisciplinary territorial analysis with visions to identify “potential spaces”. The map is a design tool to define a shared strategy of enhancement of the city and its heritage. With this paper we present one of the methodological steps of the research, a WEB-APP built upon a point clouds database and assessed through a preliminary user test. The highly descriptive 3D environment is able to collect analysis and to be enriched in a participatory way during planned activities of co-thinking. The 3D environment, improved with interviews, plans, historical pictures and other media contents, is also paired with a virtual tour to offer a different representation of the “potential spaces”. The fully boosting 3D digital technology thus represents a viable and effective solution to involve citizens and an innovative and interdisciplinary tool for knowledge advancement in the fields of architectural and urban design and heritage regeneration.
keywords	Tangible and Intangible Heritage, Co-Thinking, Trans-Scalar Approach, Narrative, Point Clouds Exploitation, Interactive Annotation, Virtual Reality
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_366
id	ecaade2022_366
authors	Geropanta, Vasiliki, Karagianni, Anna, Parthenios, Panagiotis, Ampatzoglou, Triantafyllos, Fatouros, Loukas, Simantiraki, Vasiliki, Brokos-Melissaratos, Orestis and Eleftheriadis, Dimitris
year	2022
title	Digitalization of Participatory Greening - The case of UnionYouth in Chania
doi	https://doi.org/10.52842/conf.ecaade.2022.1.469
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 469–478
summary	The contemporary climate crisis pushed communities of actors, cities and citizens to use smart technology, digital platforms, and data-based intelligence to steer creative solutions for greening in their urban ecosystems. This phenomenon brought about an increasing imperative for citizen participation and inclusion, in the co-design of green infrastructures, suggesting alternative ways to deal with the lack or misuse of public space. In this framework, this paper analyzes the case of ''UnionYouth in Chania'', a project that aims a) to build an environmental awareness strategy for Generation Z, b) to promote capacity-building processes related to climate change and environmental protection, c) actually transform the city public space through participatory processes. Specifically, the project describes the creation of a digital platform and a mobile app consisting of several engagement tools that allow interaction between the digital community of youth, the city's decision-makers, and city greening actors. Therefore, the first part of the paper talks about the necessity of promoting today's participatory processes in the city for climate change mitigation through a literature review that emerged in the last decade. The second part of the paper examines a case study, namely UnionYouth in Chania, a digital collaborative platform that promotes methods for greening the city through district-based, activity-based, and network-based redesign solutions. The third part of the paper brings about interesting reflections on the relationship between the analog and digital world, and how bottom-up processes may be an important tool in city planning. The overall scope of the analysis of the specific case study is to bring insights into the architectural world, as a means to create more bridges with citizens and communities and contribute to their greening understanding.
keywords	Climate Change, Generation Z, Green Infrastructure, Raise Awareness, Mobile Application, Participatory Design, Smart City
series	eCAADe
email
last changed	2024/04/22 07:10

_id	acadia22_256
id	acadia22_256
authors	Gerritsen, Patricia Duenas; Wissemann, Emily; García del Castillo y López, Jose Luis
year	2022
title	Designer Agency in 3D Packing of Irregular Material Stock
source	ACADIA 2022: Hybrids and Haecceities [Proceedings of the 42nd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-8-1]. University of Pennsylvania Stuart Weitzman School of Design. 27-29 October 2022. edited by M. Akbarzadeh, D. Aviv, H. Jamelle, and R. Stuart-Smith. 256-267.
summary	This paper presents a flexible computational method to simulate architectural design elements out of nonstandard and irregular sets of material stocks. This approach contributes to ongoing efforts to reduce material processing in common reuse strategies by developing a framework for human-machine design collaborations. Our three-dimensional packing method accepts as inputs user preferences with the goal of creating a framework for design that integrates creative decision-making, enabling architects to simulate and conceptualize alternative design schemes for material reuse
series	ACADIA
type	paper
email
last changed	2024/02/06 14:00

_id	ecaade2022_399
id	ecaade2022_399
authors	Johanes, Mikhael and Huang, Jeffrey
year	2022
title	Deep Learning Spatial Signature - Inverted GANs for Isovist representation in architectural floorplan
doi	https://doi.org/10.52842/conf.ecaade.2022.2.621
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, Ghent, 13-16 September 2022, pp. 621–629
summary	The advances of Generative Adversarial Networks (GANs) have provided a new experimental ground for creative architecture processes. However, the analytical potential of the latent representation of GANs is yet to be explored for architectural spatial analysis. Furthermore, most research on GANs for floorplan learning in architecture uses images as its main representation medium. This paper presents an experimental framework that uses one-dimensional periodic isovist samples and GANs inversion to recover its latent representation. Access to GANs’ latent space will open up a possibility for discriminative tasks such as classification and clustering analysis. The resulting latent representation will be investigated to discover its analytical capacity in extracting isovist spatial patterns from thousands of floorplans data. In this experiment, we hypothetically conclude that the spatial signature of the architectural floor plan could be derived from the degree of regularity of isovist samples in the latent space structure. The finding of this research will enable a new data-driven strategy to measure spatial quality using isovist and provide a new way for indexing architectural floorplan.
keywords	Machine Learning, Isovist, Latent Representation, GANs Inversion, Spatial Signature
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ascaad2022_062
id	ascaad2022_062
authors	Kanter, Jordan; Quinteros, Kamil
year	2022
title	Gestural Design: Hand Tracking for Digital Drawing
source	Hybrid Spaces of the Metaverse - Architecture in the Age of the Metaverse: Opportunities and Potentials [10th ASCAAD Conference Proceedings] Debbieh (Lebanon) [Virtual Conference] 12-13 October 2022, pp. 30-42
summary	Computational design is increasingly interested in the active feedback between the user/designer and the digital space. Often, our initial instinct as designers comes from a gesture, a movement of the hands that gets translated into sketches and 3D models via the tools available to us. While the physical realm allows for muscle memory, tactile feedback, and creative output via movement, digital design often negates the body of the designer as it sequesters us into a screen-mouse-hand relationship. Moreover, current CAD software tools often reinforce this standardization, further limiting the potential of physical bodily gestures as a vehicle for architectural form-making. Seeking new opportunities for a gestural interface, this research explores how Machine Learning and parametric design tools can be used to translate active movements and gestural actions into rich and complex digital models without the need of specialized equipment. In this paper, we present an open-source and economically accessible methodology for designers to translate hand movements into the digital world, implementing the MediaPipe Hands tracking library. In developing this workflow, this research explores opportunities to create more direct, vital links between expressive gesture and architectural form, with an emphasis on creating platforms that are accessible not only to design experts, but also the broader public.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	ecaade2022_203
id	ecaade2022_203
authors	Kim, Frederick Chando and Huang, Jeffrey
year	2022
title	Perspectival GAN - Architectural form-making through dimensional transformation
doi	https://doi.org/10.52842/conf.ecaade.2022.1.341
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 341–350
summary	With the ascendance of Generative Adversarial Networks (GAN), promising prospects have arisen from the abilities of machines to learn and recognize patterns in 2D datasets and generate new results as an inspirational tool in architectural design. Insofar as the majority of ML experiments in architecture are conducted with imagery based on readily available 2D data, architects and designers are faced with the challenge of transforming machine-generated images into 3D. On the other hand, GAN-generated images are found to be able to learn the 3D information out of 2D perspectival images. To facilitate such transformation from 2D and 3D data in the framework of deep learning in architecture, this paper explores making new architectural forms from flat GAN images by employing traditional tools of projective geometry. The experiments draw on Brook Taylor’s 19th- century theorem of inverse projection system for creating architectural form from perspectival information learned from GAN images of Swiss alpine architecture. The research develops a parametric tool that automates the dimensional transformation of 2D images into 3D architectural forms. This research identifies potential synergic interactions between traditional tools and techniques of architects and deep learning algorithms to achieve collective intelligence in designing and representing creative architecture forms between humans and machines.
keywords	Machine Learning, GAN, Architectural Form, Perspective Projection, Inverse Perspective, Digital Representation
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_228
id	ecaade2022_228
authors	Körner, Andreas
year	2022
title	Chromogenic Composites - A case study combining thermochromics with heat transfer simulations and digital fabrication in architectural education
doi	https://doi.org/10.52842/conf.ecaade.2022.1.291
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 291–300
summary	Over the last few decades, environmental considerations have become increasingly important in architecture. To predict and simulate material changes and environmental forces can help architects to articulate surfaces. In architectural education, an increasing amount of the curricula are engaging with aspects of energy design, sustainability, and environmental simulations. The successful integration of related novel technologies in education has been demonstrated in the past. This paper documents a technical seminar that focused on the combination of digital environmental simulations and smart materials to create chromogenic prototypes for environmentally responsive architectural composites. Thermochromic chromogenics are substances that reversibly change colour depending on temperature. Specifically, the task was to come up with novel techniques to combine such materials with varying substrates to achieve dynamic panels. The course design was informed by a variety of design research and learning concepts. Students were asked to use digital heat transfer simulations to predict the smart material changes of computationally designed panels. Each of the eight idiosyncratic prototypes was modified with a variety of techniques and coated with thermochromic ink to achieve complex heat signature patterns. The resulting chromogenic composites were documented and analyzed using photos and infrared thermography. The seminar’s results showed that the three aspects (simulation, material, fabrication) can help to introduce eco-relevant technologies to design education. For this paper, both the outcomes and the course design itself were reviewed to better understand the co-creation process of the three aspects. This evaluation provided a rich repertoire of possibilities to combine different technologies for creative environmental design in architecture; all while maintaining an engaging teaching environment.
keywords	Education, Smart Materials, Simulation, Prototyping, Heat Transfer
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_361
id	caadria2022_361
authors	Lok, Leslie and Bae, Jiyoon
year	2022
title	Timber De-Standardized 2.0 : Mixed Reality Visualizations and User Interface for Processing Irregular Timber
doi	https://doi.org/10.52842/conf.caadria.2022.2.121
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 121-130
summary	Timber De-Standardized 2.0†is a mixed reality (MR) user interface (UI) that utilizes timber waste produced by manufacturing dimensional lumber, suggesting an expanded notion for "material usability‚ in timber construction. The expanded notion of designing with discarded logs not only requires new tools and technologies for cataloguing, structuring, and fabricating. It also relies on new methods and platforms for the visualization and design of these structures. As a†MR†UI,†Timber De-Standardized†enables professionals and non-professionals alike to seamlessly design with irregular logs and to create viable structural systems using an intuitive†MR†environment. In order to develop a†MR†environment with this level of competency, the research aims to finesse the visualization techniques in the immersive full-scale†3D†environment and to minimize the use of alternative 2D UI(s). The research methodology†focuses on†(1) cataloguing and extracting basic properties of various tree logs, (2)†refining mesh visualization for better user interaction, and†(3)†developing†the†MR†UI to increase user design agency with custom menu lists and operations.†This methodology will extend the usability of†MR†UI protocols to a broader audience while democratizing design and enabling the user as co-creator.
keywords	Irregular Tree Logs, Wood Construction, Augmented and Mixed Realities, Mixed Reality User Interface, Co-Creative Design, Digital representation and visualization, SDG 9, SDG 12, SDG 13
series	CAADRIA
email
last changed	2022/07/22 07:34

For more results click below: