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 676

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

_id	ascaad2022_085
id	ascaad2022_085
authors	Cicek, Selen; Koc, Mustafa; Korukcu, Berfin
year	2022
title	Urban Map Generation in Artist's Style using Generative Adversarial Networks (GAN)
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. 264-282
summary	Artificial Intelligence is a field that is able to learn from existing data to synthesize new ones using deep learning methods. Using Artificial Neural Networks that process big datasets, complex tasks and challenges become easily resolved. As the zeitgeist suggests, it is possible to produce novel outcomes for future projections by applying various machine learning algorithms on the generated data sets. In that context, the focus of this research is exploring the reinterpretation of 21st century urban plans with familiar artist styles using different subtypes of deep-learning-based generative adversarial networks (GAN) algorithms. In order to explore the capabilities of urban map transformation with machine learning approaches, two different GAN algorithms which are cycleGAN and styleGAN have been applied on the two main data sets. First data set, the urban data set, contains 50 cities urban plans in .jpeg format collected according to the diversity of the urban morphologies. Whereas the second data set is composed of four well-known artist’s paintings, that belong to various artistic movements. As a result of training the same data sets with different GAN algorithms and epoch values were compared and evaluated. In this respect, the study not only investigates the reinterpretation of stylistic urban maps and shows the discoverability of new representation techniques, but also offers a comparison of the use of different image to image translation GAN algorithms.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	caadria2022_272
id	caadria2022_272
authors	Dong, Zhiyong
year	2022
title	Perceiving Fabric Immersed in Time, an Exploration of Urban Cognitive Capabilities of Neural Networks
doi	https://doi.org/10.52842/conf.caadria.2022.1.263
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. 263-272
summary	City develops gradually with the lapse of time. Cities, as a ‚container‚, are injected new urban elements along the trajectory of the times and the progress of human civilization, constructing the historical structures involved past, present and future. Thus, the cultural information of each era is preserved in the urban fabric together and urban fabric features are complex and rich, which are difficult to capture in traditional design methods. In this paper, we try to use Generative Adversarial Networks (GAN), one of the neural network algorithms, to explore the inner rules of complex urban morphological features and realize the perception of the urban fabric. Neural networks are innovatively applied to the larger and more complex city generation in this experiment. First, we collect European urban fabric as the dataset, then label data to facilitate machine training, use GAN to learn the feature of the dataset by adjusting parameters, and analyze the effect of the generated results. The automatic feature learning capability of the neural networks is used to summarize the inherent patterns and rules in urban development which is difficult for human to discover.
keywords	Deep Learning, Generative Adversarial Networks, Generative Design, Morphology Cognition, Urban Fabric, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_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	caadria2022_114
id	caadria2022_114
authors	Dong, Zhiyong, Lin, Jinru, Wang, Siqi, Xu, Yijia, Xu, Jiaqi and Liu, Xiao
year	2022
title	Where Will Romance Occur, A New Prediction Method of Urban Love Map through Deep Learning
doi	https://doi.org/10.52842/conf.caadria.2022.1.213
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. 213-222
summary	Romance awakens fond memories of the city. Finding out the relationship between romantic scene and urban morphology, and providing a prediction, can potentially facilitate the better urban design and urban life. Taking the Yangtze River Delta region of China as an example, this study aims to predict the distribution of romantic locations using deep learning based on multi-source data. Specifically, we use web crawlers to extract romance-related messages and geographic locations from social media platforms, and visualize them as romance heatmap. The urban environment and building features associated with romantic information are identified by Pearson correlation analysis and annotated in the city map. Then, both city labelled maps and romance heatmaps are fed into a Generative Adversarial Networks (GAN) as the training dataset to achieve final romance distribution predictions across regions for other cities. The ideal prediction results highlight the ability of deep learning techniques to quantify experience-based decision-making strategies that can be used in further research on urban design.
keywords	Romance Heatmap, Generative Adversarial Networks, Deep Learning, Big Data Analysis, Correlation Analysis, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_279
id	caadria2022_279
authors	Kim, Dongyun, Guida, George and Garcia del Castillo y Lopez, Jose Luis
year	2022
title	PlacemakingAI : Participatory Urban Design with Generative Adversarial Networks
doi	https://doi.org/10.52842/conf.caadria.2022.2.485
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. 485-494
summary	Machine Learning (ML) is increasingly present within the architectural discipline, expanding the current possibilities of procedural computer-aided design processes. Practical 2D design applications used within concept design stages are however limited by the thresholds of entry, output image fidelity, and designer agency. This research proposes to challenge these limitations within the context of urban planning and make the design processes accessible and collaborative for all urban stakeholders. We present PlacemakingAI, a design tool made to envision sustainable urban spaces. By converging supervised and unsupervised Generative Adversarial Networks (GANs) with a real-time user interface, the decision-making process of planning future urban spaces can be facilitated. Several metrics of walkability can be extracted from curated Google Street View (GSV) datasets when overlayed on existing street images. The contribution of this framework is a shift away from traditional design and visualization processes, towards a model where multiple design solutions can be rapidly visualized as synthetic images and iteratively manipulated by users. In this paper, we discuss the convergence of both a generative image methodology and this real-time urban prototyping and visualization tool, ultimately fostering engagement within the urban design process for citizens, designers, and stakeholders alike.
keywords	Machine Learning, Generative Adversarial Networks, user interface, real-time, walkability, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	cdrf2022_274
id	cdrf2022_274
authors	Zhiyong Dong and Jinru Lin
year	2022
title	Nolli Map: Interpretation of Urban Morphology Based on Machine Learning
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_24
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	Nolli map is the earliest diagram tool to simplify and quantify urban form, which most intuitively reflects the spatial layout of tangible elements in the city. The urban morphology contains its inherent evolutionary laws. Exploring the inner rules of cities is helpful for people to conduct urban research and design. Unlike the traditional research methods of urban morphology, the neural network algorithm provides us with new ideas for understanding urban morphology. In this experiment, we label 136 European cities samples in the rules of Nolli map as a training set for machine learning. We use Generative Adversarial Networks (GAN) for multiple mapping experiments. The generated images present recognizable and plausible images of the urban fabric. The results show that the machine can learn the inherent laws of complex urban fabrics, which expands a new applied method for the study of urban morphology.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ecaade2022_218
id	ecaade2022_218
authors	Bank, Mathias, Sandor, Viktoria, Schinegger, Kristina and Rutzinger, Stefan
year	2022
title	Learning Spatiality - A GAN method for designing architectural models through labelled sections
doi	https://doi.org/10.52842/conf.ecaade.2022.2.611
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. 611–619
summary	Digital design processes are increasingly being explored through the use of 2D generative adversarial networks (GAN), due to their capability for assembling latent spaces from existing data. These infinite spaces of synthetic data have the potential to enhance architectural design processes by mapping adjacencies across multidimensional properties, giving new impulses for design. The paper outlines a teaching method that applies 2D GANs to explore spatial characteristics with architectural students based on a training data set of 3D models of material-labelled houses. To introduce a common interface between human and neural networks, the method uses vertical slices through the models as the primary medium for communication. The approach is tested in the framework of a design course.
keywords	AI, Architectural Design, Materiality, GAN, 3D, Form Finding
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_411
id	ecaade2022_411
authors	Cesar Rodrigues, Ricardo, Rubio Koga, Renan, Hitomi Hirota, Ercilia and Bertola Duarte, Rovenir
year	2022
title	Mapping Space Allocation with Artificial Intelligence - An approach towards mass customized housing units
doi	https://doi.org/10.52842/conf.ecaade.2022.2.631
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. 631–640
summary	Artificial Intelligence represents a substantial part of the available tools on architectural design, especially for Space Layout Planning (SLP). At the same time, the challenge of Mass Customization (MC) is to increase the product variety while maintaining a good cost-benefit ratio. Thus, this research aims to identify new, valid, and easily understandable data patterns through human-machine interaction in an attempt to deal with the challenges of MC during the early phases of SLP. The Design Science Research method was adopted to develop a digital artifact based on deep generative models and a reverse image search engine. The results indicate that the artifact can deliver a series of design alternatives and enhance the navigation process in the solution space, besides giving key insights on dataset design for further research.
keywords	Floor plans, Generative Adversarial Networks, Mass Customization
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_367
id	ecaade2022_367
authors	Doumpioti, Christina and Huang, Jeffrey
year	2022
title	Field Condition - Environmental sensibility of spatial configurations with the use of machine intelligence
doi	https://doi.org/10.52842/conf.ecaade.2022.2.067
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. 67–74
summary	Within computational environmental design (CED), different Machine Learning (ML) models are gaining ground. They aim for time efficiency by automating simulation and speeding up environmental performance feedback. This study suggests an approach that enhances not the optimization but the generative aspect of environmentally driven ML processes in architectural design. We follow Stan Allen's (2009) idea of 'field conditions' as a bottom-up phenomenon according to which form and space emerge from local invisible and dynamic connections. By employing parametric modeling, environmental analysis data, and conditional Generative Adversarial Networks [cGAN] we introduce a generative approach in design that reverses the typical design process of going from formal interpretation to analysis and encourages the emergence of spatial configurations with embedded environmental intelligence. We call it Intensive-driven Environmental Design Computation [IEDC], and we employ it in a case study on a residential building typology encountered in the Mediterranean. The paper describes the process, emphasizing dataset preparation as the stage where the logic of field conditions is established. The proposed research differentiates from cGAN models that offer automatic environmental performance predictions to one that spatial predictions stem from dynamic fields.
keywords	Field Architecture, Environmental Design, Generative Design, Machine Learning, Residential Typologies
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_78
id	ecaade2022_78
authors	Eroglu, Ruºen and Gül, Leman Figen
year	2022
title	Architectural Form Explorations through Generative Adversarial Networks - Predicting the potentials of StyleGAN
doi	https://doi.org/10.52842/conf.ecaade.2022.2.575
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. 575–582
summary	In recent years, generative models have been rapidly transforming into a broad field of research, and artificial intelligence (AI) works are increasing. Since deep learning technologies such as Generative Adversarial Networks (GANs) providing synthesized new images are becoming more accessible, researchers in the design and related fields are very much interested in adapting GANs into practice. Especially, StyleGAN has a strong capability for image learning, reconstruction simulation, and absorbing the pixel characteristics of images in the input dataset. StyleGAN also produces similar imitation outputs and summarizes all the input data into one "average output". The study aims to reveal the potential of these outputs that can be employed as a visual inspiration aid for designers. This article will discuss the outputs of the experiments, findings, and prospects of StyleGAN.
keywords	Artificial Intelligence, Machine Learning, Generative Adversarial Networks, StyleGAN
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_44
id	ecaade2022_44
authors	Güzelci, Orkan Zeynel
year	2022
title	Machine Learning in Predicting Section Drawings - Case of Anatolian Seljuk Kümbets
doi	https://doi.org/10.52842/conf.ecaade.2022.2.169
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. 169–176
summary	Funerary structures called kümbet emerged as a unique typology during the Anatolian Seljuk period (1077-1307). This study introduces a machine learning (ML) based model to predict sections of kümbets to complete their missing parts. The proposed ML-based model employs the Pix2Pix method, which is a subset of conditional Generative Adversarial Networks (cGAN).The model is trained over a coupled dataset (interior space and exterior shell) of section drawings. Then, the model is validated by predicting overall shape (exterior shell) for a given input (interior space). The outcomes of the validation phase are evaluated objectively by using structural similarity method (SSIM). Initial findings of the implementation show that the proposed ML-based model has the potential to be used as a design decision support tool for further restitution and renovation works.
keywords	Anatolian Seljuk Architecture, Kümbet, Pix2Pix, Machine Learning, Section
series	eCAADe
email
last changed	2024/04/22 07:10

_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_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	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_113
id	ecaade2022_113
authors	van Son, Nicholas A. and Prado, Marshall
year	2022
title	Computational Schematic Design Utilizing Self-Organizing Programmatic Agents - A novel approach to visualizing and organizing urban and architectural data
doi	https://doi.org/10.52842/conf.ecaade.2022.2.095
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. 95–104
summary	Architectural design requires the negotiation of a wide variety of often conflicting constraints and conditions. This puts a tremendous burden on designers to understand and evaluate all the design and site parameters in the conceptual phase of the project. Design methodologies that utilize conventional means of representation such as site diagrams, maps, or other orthographic projections may not be adequate to produce truly integrative design solutions. They often simplify conditions for user clarity or eliminate volumetric and temporal data entirely. As computational design tools develop and the mapping of georeferenced urban data becomes more commonplace, it becomes possible to integrate spatial information into design strategies and evaluate various relationships more effectively. Taking clues from medical imaging, voxel data is used to represent volumetric gradients in material properties and densities of spatial conditions. This method can be used to generate morphogenic spatial analysis of an existing site. The research presented here explores how self-organizing programmatic agents can use this analysis and embedded behaviors to visualize performative schematic design scenarios. These agents, which represent a variety of functional spaces, programmatic requirements, design constraints, and value sets, can negotiate the myriad of environmental and socio- economic site conditions as well as interact with other adaptive programmatic spaces. Each agent can iteratively search for the space that best suits the desired conditions of its program. Various agents compete for space so the overall performance of the spatial arrangement is maximized. This self-organizing spatial system presents a novel and viable means for designers to more effectively implement both urban data and computational design methods into architectural design scenarios.
keywords	Agent-based Modeling, Voxels, Generative Design, Self-Organizing, Urban Data Mapping, Optimization, Spatial Analysis
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_172
id	ecaade2022_172
authors	Vugreshek, Zvonko
year	2022
title	Discrete Differences between Aggregate Systems for Generative Urban and Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2022.2.029
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. 29–38
summary	The activation of aggregate systems, procedural generation, and other models of discrete computation result in different organizations and formal outcomes. Some differences seem blurry but are relevant to understand in order to govern the computational design process in the specific domain. They are developing around empiric principles, are based on discrete automation rule sets, and are intertwined in various ways. The paper presents and describes some differences and communalities between each system. Its goal is to support the computational designer, architect or urban planner in the decision-making process and choice of which system could work best in a given context and to solve a specific problem. An introduction into aggregation or automation will serve as a foundation for the research. The discrete systems Cellular Automata, Wave Function Collapse, Graph-Grammar Aggregation will be described. In this paper, the latter is specified as selection-based-aggregation. Diffusion-Limited Aggregation (DLA), which is regarded as an early translation of natural behaviour into scripted nature will serve as a framework. In a next step potential and utilization of these discrete systems in expanding the language of architectural and urban morphology will be experimentally demonstrated and compared. The paper concludes by suggesting a current state of development and potential adaptation of the methods for broader use within the architectural and urban design paradigm of developing methods for the creation of new computational typologies.
keywords	Discrete Aggregation, Cellular Automata, Procedural Generation, Urban Morphology Generation, Wave Function Collapse
series	eCAADe
email
last changed	2024/04/22 07:10

_id	cdrf2022_209
id	cdrf2022_209
authors	Yecheng Zhang, Qimin Zhang, Yuxuan Zhao, Yunjie Deng, Feiyang Liu, Hao Zheng
year	2022
title	Artificial Intelligence Prediction of Urban Spatial Risk Factors from an Epidemic Perspective
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_18
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	From the epidemiological perspective, previous research methods of COVID-19 are generally based on classical statistical analysis. As a result, spatial information is often not used effectively. This paper uses image-based neural networks to explore the relationship between urban spatial risk and the distribution of infected populations, and the design of urban facilities. We take the Spatio-temporal data of people infected with new coronary pneumonia before February 28 in Wuhan in 2020 as the research object. We use kriging spatial interpolation technology and core density estimation technology to establish the epidemic heat distribution on fine grid units. We further examine the distribution of nine main spatial risk factors, including agencies, hospitals, park squares, sports fields, banks, hotels, Etc., which are tested for the significant positive correlation with the heat distribution of the epidemic. The weights of the spatial risk factors are used for training Generative Adversarial Network models, which predict the heat distribution of the outbreak in a given area. According to the trained model, optimizing the relevant environment design in urban areas to control risk factors effectively prevents and manages the epidemic from dispersing. The input image of the machine learning model is a city plan converted by public infrastructures, and the output image is a map of urban spatial risk factors in the given area.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ecaade2022_153
id	ecaade2022_153
authors	Zhong, Ximing, Fricker, Pia, Yu, Fujia, Tan, Chuheng and Pan, Yuzhe
year	2022
title	A Discussion on an Urban Layout Workflow Utilizing Generative Adversarial Network (GAN) - With a focus on automatized labeling and dataset acquisition
doi	https://doi.org/10.52842/conf.ecaade.2022.2.583
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. 583–592
summary	Deep Learning (DL) has recently gained widespread attention in the automation of urban layout processes. This study proposes a rule-based and Generative Adversarial Network (GAN) workflow to automatically select and label urban datasets to train customized GAN models for the generation of urban layout proposals. The developed workflow automatically collects and labels urban typology samples from open-source maps. Furthermore, it controls the results of the GAN process with labels and provides real-time urban layout suggestions based on a co-design process. The conducted case study shows that the average value of the GAN results, trained from an automatically generated dataset, meets the site's requirements. The developed co-design strategy allows the architect to control the GAN process and perform iterations on urban layouts. The research addresses the research gap in GAN applications in the field of urban design and planning. Many studies have demonstrated that training the (GAN) model by labeling enables machines to learn urban morphological features and urban layout logic. However, two research gaps remain: (1) The manual filtering of GAN urban sample datasets to fit site-specific design requirements is very time-consuming. (2) Without a suitable data labeling method, it is difficult to manage the GAN process in such a manner to facilitate the meeting of overriding design requirements.
keywords	Deep Learning, Generative Adversarial Network (GAN), Urban Layout Process, Automatic Dataset Construction, Co-design
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_273
id	ecaade2022_273
authors	Zhuang, Xinwei
year	2022
title	Rendering Sketches - Interactive rendering generation from sketches using conditional generative adversarial neural network
doi	https://doi.org/10.52842/conf.ecaade.2022.1.517
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. 517–524
summary	Architects use sketches in the early design phase to organize and elaborate their initial ideas, and those initial sketches often support ideation for the final design. However, the sketches in the early design phase tend to be abstract and hard to interpret. Minimal prior works provide tools for quick visualization of the initial sketch. This study provides a scheme for architects and designers to generate preliminary renderings in the early design stage. In this study, we use conditional generative adversarial networks (cGAN) as the frame and introduces an updater network to the existing cGAN to support the iterative design process. A sketch serves as input to see the rendering and update the sketch based on the generated renderings by adding more resolution and details. The network is able to generate a reasonable rendering from the single-image network, and is able to update the renderings iteratively via the updater network. The dataset is collected from residential buildings exclusively, but the architectural categories can be expanded to other types of buildings in the future. Results show that the proposed scheme is able to provide reasonable renderings from sketches, and the generated rendering can be updated with a higher level of details within a second if the user provides a more detailed sketch. The contribution of this study includes introducing an updater network to the existing algorithm to enable iterative input and provides an alternative enhancement approach to the resolution of the generated image.
keywords	Computer Aided Design, Early Design Phase, Conditional Generative Adversarial Neural Network, Human Computer Interaction
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_45
id	caadria2022_45
authors	Boim, Anna, Dortheimer, Jonathan and Sprecher, Aaron
year	2022
title	A Machine-Learning Approach to Urban Design Interventions In Non-Planned Settlements
doi	https://doi.org/10.52842/conf.caadria.2022.1.223
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. 223-232
summary	This study presents generative adversarial networks (GANs), a machine-learning technique that can be used as an urban design tool capable of learning and reproducing complex patterns that express the unique spatial qualities of non-planned settlements. We report preliminary experimental results of training and testing GAN models on different datasets of urban patterns. The results reveal that machine learning models can generate development alternatives with high morphological resemblance to the original urban fabric based on the suggested training process. This study contributes a methodological framework that has the potential to generate development alternatives sensitive to the local practices, thereby promoting preservation of traditional knowledge and cultural sustainability.
keywords	Non-planned settlements, Cultural Sustainability, Machine Learning, Generative Adversarial Networks, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

For more results click below: