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 657

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

_id	caadria2022_227
id	caadria2022_227
authors	Stuart-Smith, Robert and Danahy, Patrick
year	2022
title	Visual Character Analysis within Algorithmic Design: Quantifying Aesthetics Relative to Structural and Geometric Design Criteria
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. 131-140
doi	https://doi.org/10.52842/conf.caadria.2022.1.131
summary	Buildings are responsible for 40% of world C02 emissions and 40% of the world's raw material consumption. Designing buildings with a reduced material volume is essential to securing a post-carbon built environment and supports a more affordable, accessible architecture. Architecture‚s material efficiency is correlated to structural efficiency however, buildings are seldom optimal structures. Architects must resolve several conflicting design criteria that can take precedence over structural concerns, while material-optimization is also impacted from limited means to quantitatively assess aesthetic decisions. Flexible design methods are required that can adapt to diverse constraints and generate filagree material arrangements, currently infeasible to explicitly model. A novel approach to generative topological design is proposed employing a custom multi-agent method that is adaptive to diverse structural conditions and incorporates quantitative analysis of visual formal character. Computer vision methods Gabor filtering, Canny Contouring and others are utilized to evaluate the visual appearance of designs and encode these within quantitative metrics. A matrix of design outcomes for a pavilion are developed to test adaptation to different spatial arrangements. Results are evaluated against visual character, structural, and geometric methods of analysis and demonstrate a limited set of aesthetic design criteria can be correlated with structural and geometric data in a quantitative metric.
keywords	Generative/Algorithmic Design, Computer Vision, Environmental Performance, Multi-Agent Systems, Visual Character Analysis, SDG 10, SDG 11, SDG 9, SDG 12, SDG 13
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	sigradi2022_270
id	sigradi2022_270
authors	Arenas, Felipe; Banda, Pablo
year	2022
title	Ludo faber alumni: playful experiences of digital manufacturing for the appropriation of educational spaces
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. 503–514
summary	The present study is inserted in the learning context of the Architecture career of 40 students in a course of Applied Digital Fabrication. It seeks to explore the design possibilities that are produced by permeating game design features with digital architectural design and digital fabrication with each other. What spatial design potentials appear when introducing and intermingling the notions of Homo Ludens and Homo Faber in architectural generative design systems?
keywords	Digital fabrication, Gamification, Generative design, rule-based design
series	SIGraDi
email
last changed	2023/05/16 16:56

_id	ijac202220101
id	ijac202220101
authors	Bao, Ding Wen; Xin Yan, Yi Min Xie
year	2022
title	Encoding topological optimisation logical structure rules into multi-agent system for architectural design and robotic fabrication
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 1, pp. 7–17
summary	Natural phenomena have been explored as a source of architectural and structural design inspiration with different approaches undertaken within architecture and engineering. The research proposes a connection between two dichotomous principles: architectural complexity and structural efficiency through a hybrid of natural phenomena, topology optimisation and generative design. Both Bi-directional Evolutionary Structural Optimisation (BESO) and multi-agent algorithms are emerging technologies developed into new approaches that transform architectural and structural design, respectively, from the logic of topology optimisation and swarm intelligence. This research aims to explore a structural behaviour feedback loop in designing intricate functional forms through encoding BESO logical structure rules into the multi-agent algorithm. This research intends to study and evaluate the application of topology optimisation and multi-agent system in form-finding and later robotic fabrication through a series of prototypes. It reveals a supposition that the structural behaviour-based design method matches the beauty and function of natural appearance and structure. Thus, a new exploration of architectural design and fabrication strategy is introduced, which benefits the collab- oration among architects, engineers and manufacturers. There is the potential to seek the ornamental complexities in architectural forms and the most efficient use of material based on structural performance in the process of generating complex geometry of the building and its various elements.
keywords	Swarm intelligence, multi-agent, bi-directional evolutionary structural optimisation (BESO), intricate architectural form, efficient structure
series	journal
last changed	2024/04/17 14:29

_id	caadria2022_507
id	caadria2022_507
authors	Bolojan, Daniel, Vermisso, Emmanouil and Yousif, Shermeen
year	2022
title	Is Language All We Need? A Query Into Architectural Semantics Using a Multimodal Generative Workflow
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. 353-362
doi	https://doi.org/10.52842/conf.caadria.2022.1.353
summary	This project examines how interconnected artificial intelligence (AI)-assisted workflows can address the limitations of current language-based models and streamline machine-vision related tasks for architectural design. A precise relationship between text and visual feature representation is problematic and can lead to "ambiguity‚ in the interpretation of the morphological/tectonic complexity of a building. Textual representation of a design concept only addresses spatial complexity in a reductionist way, since the outcome of the design process is co-dependent on multiple interrelated systems, according to systems theory (Alexander 1968). We propose herewith a process of feature disentanglement (using low level features, i.e., composition) within an interconnected generative adversarial networks (GANs) workflow. The insertion of natural language models within the proposed workflow can help mitigate the semantic distance between different domains and guide the encoding of semantic information throughout a domain transfer process.
keywords	Neural Language Models, GAN, Domain Transfer, Design Agency, Semantic Encoding, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_258
id	caadria2022_258
authors	Chen, Hao, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2022
title	Developing an Augmented Reality System with Real-Time Reflection for Landscape Design Visualization, Using Real-Time Ray Tracing Technique
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. 89-98
doi	https://doi.org/10.52842/conf.caadria.2022.1.089
summary	In landscape design, visualization of a new design on the site with clients can greatly improve communication efficiency and reduce communication costs. The use of augmented reality (AR) allows the projection of design models into the real environment, but the relationship between the models and the physical environment, such as reflections, which are often thoughtfully considered in waterfront landscape design, is difficult to express in existing AR systems. The aim of this study is to accurately render and express the reflections of virtual models in the physical environment in an AR system. Different from traditional rasterized rendering, this study used physically correct ray-tracing algorithms for reflection rendering calculations. Using a smartphone and a computer, we first constructed a basic AR system using a game engine and then performed ray-tracing computations using a shader kernel in the game engine. Finally, we combined the rendering results of reflections with the video stream from a smartphone camera to achieve the reflection effect of a virtual model in a physical environment. Both designers and clients could review the design with a realistic reflection on an actual water surface and discuss design decisions through this system.
keywords	Augmented reality (AR), reflection, landscape design, interactive visualization, real-time rendering, planar reflection, real-time ray tracing, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	cdrf2022_396
id	cdrf2022_396
authors	Chengbi Duan, Suyi Shen, Dingwen Bao, and Xin Yan
year	2022
title	Exploration and Design of the Contemporary Bracket Set Through Topology Optimization
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_34
summary	Dou Gong, pronounced in Chinese, and known as Bracket Set, is a vital support component in the ancient wooden tectonic systems. It is located between the column and the beam and connects the eave and pillar, making the heavy roof extend out of the eaves longer. The development of the bracket set is entirely a microcosm of the development of ancient Chinese architecture; the aesthetic structure and oriental artistic temperament behind the bracket make it gradually become the cultural and spiritual symbol of traditional Chinese architecture. In the contemporary era, inheriting and developing the bracket set has become an essential issue. This paper introduces the topological optimization method bi-directional evolutionary structural optimization (BESO) for form-finding. Through analyzing the development trend of bracket set and mechanical structure, the authors integrate 2D and 3D optimization methods and apply the hybrid methods to form-finding. This research aims to design a new bracket set corresponding to “structural performance-based aesthetics.“ The workflow proposed in this paper is valuable for architrave and other traditional building components.
series	cdrf
email
last changed	2024/05/29 14:03

_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	acadia22_224
id	acadia22_224
authors	Coersmeier, Jonas; Nanasca, James; Man Hin, Ivan Yan; Blasetti, Ezio
year	2022
title	Nanotectonica SEM-GAN
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. 224-243.
summary	The present study, Nanotectonica SEM-GAN, focuses on two processes for image production, one based in the field of nanotechnology and the other in machine learning: Scanning Electron Microscopy (SEM) and Generative Adversarial Networks (GAN). It establishes commonalities of these routines as they pertain to aesthetics and design methodology, and it explores methods of spatializing and materializing images produced in their interaction. The study of transposing rich image material to three-dimensional geometry and material artifact is considered relevant not only to the particular study at hand, but also to the general problem of image-based machine learning techniques when applied in the spatial design disciplines. A third process, Robotic Incremental Metal Forming (RIMF), advances the aesthetic language of SEM-GAN through the sculptural method of the relief.
series	ACADIA
type	paper
email
last changed	2024/02/06 14:00

_id	ecaade2022_221
id	ecaade2022_221
authors	Delikanli, Burak and Gül, Leman Figen
year	2022
title	Towards to the Hyperautomation - An integrated framework for Construction 4.0: a case of Hookbot as a distributed reconfigurable robotic assembly system
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. 389–398
doi	https://doi.org/10.52842/conf.ecaade.2022.2.389
summary	Almost every technological and industrial concept changes the built environment around us and our understanding of the architectural practice. Recently, Hyperautomation, an all-encompassing digital transformation with the help of advanced techniques, has been presented as a game-changing concept that can affect any industry. Despite this promising concept, the Architecture, Engineering, and Construction (AEC) industry seems far behind the latest technological breakthroughs and automation of processes compared to other industries. Therefore, this study provides a better understanding of adopting the novel Hyperautomation paradigm in the AEC industry by focusing on Industry 4.0. In this context, the first section introduces the Construction 4.0 concept, its counterpart in the AEC industry, briefly mentions fundamental approaches and indicates the need for a framework. The second section introduces an integrated framework throughout the entire building life-cycle for design and construction processes and exemplifies the stages in an autonomous system and their interrelationships. The third section presents a hypothetical case, a distributed reconfigurable robotic assembly system, and the assembler ‘HookBot’ to understand the relationships in an autonomous system better. The last section discusses the place of the Hyperautomation paradigm in architecture.
keywords	Autonomy, Autonomous Systems, Construction 4.0, Assembly Robotics
series	eCAADe
email
last changed	2024/04/22 07:10

_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
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
doi	https://doi.org/10.52842/conf.caadria.2022.1.263
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	ijac202220306
id	ijac202220306
authors	Duclos-Prévet, Claire; François Guéna; Mariano Efron
year	2022
title	Constraint handling methods for a generative envelope design using genetic algorithms: The case of a highly constrained problem
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 3, pp. 587–609
summary	The use of genetic algorithms as generative and performance design techniques often involves, in practice, constraint handling, which can be a complex task. Moreover, environmental simulations are computationally expensive and managing constraints can avoid wasting time on infeasible solutions. Despite these two incentives, and the benefits of an immense literature, both applied and theorical, on constrained optimization, there are only few guidelines and tools directly applicable by architects to address this issue. This paper proposes to fill this gap by identifying, classifying, and implementing different constraint management techniques available to architects. Seven methods have been tested for a highly constrained envelope design problem, consisting in the optimization of a sun-shading system. Three of them are easily replicable to different types of projects while the four others need to find a problem-specific heuristic. It appears that the second category is more efficient but implies the use of generative techniques that are more difficult to implement than parametric models
keywords	Optimization under constraint, performative envelope design, generative and sustainable design, agent-based modeling, multiobjective genetic algorithm, visual comfort
series	journal
last changed	2024/04/17 14:30

_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
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
doi	https://doi.org/10.52842/conf.ecaade.2022.2.575
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	acadia22_662
id	acadia22_662
authors	Furgiuele, Antonio; Ergezer, Mehmet; Zaman, Cagri Hakan
year	2022
title	Towards an Adversarial Architecture
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. 662-671.
summary	A key technological weakness of artificial intelligence (AI) is adversarial images, a constructed form of image-noise added to an image that can manipulate machine learning algorithms but is imperceptible to humans. Adversarial Architecture explores the application of adversarial images to the built environment and develops a new method of design agency to directly engage artificial intelligence. Embedding a layer of information to physical surfaces that is only perceptible to machines has many potential applications, such as uniquely identifying and tracking objects, embedding accessibility features directly to surfaces, and counter-surveillance systems in different scales.
series	ACADIA
type	paper
email
last changed	2024/02/06 14:04

_id	ecaade2022_250
id	ecaade2022_250
authors	Garcia del Castillo y Lopez, Jose L.
year	2022
title	The Digital Touch - Towards novel modeling frameworks for robotically-enhanced marble sculpting
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. 37–46
doi	https://doi.org/10.52842/conf.ecaade.2022.1.037
summary	In this paper, two case studies on digital modeling for robotically-enabled marble carving are presented. In the first one, an interactive, gesture-based modeling framework was developed to sculpt a large, undulating and ultra-thin marble surface. On the second one, an integrated 3D-scanning-to-milling solution was created, in order to groove a superficial pattern on the surface of a discarded marble boulder. The cases evidence the power of tangible interaction to serve as input to novel digitally-aided marble sculpting processes, and the capacity of integrated generative design workflows to create consistent solutions to variable conditions, in this case, with a particular focus on sustainability and reclaiming of scrap materials.
keywords	Robotic Fabrication, Generative Design, Modeling, Sculpting
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_195
id	ecaade2022_195
authors	Garcia, Sara and Leitao, António
year	2022
title	Interfaces for Design Space Exploration
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. 331–340
doi	https://doi.org/10.52842/conf.ecaade.2022.1.331
summary	A Generative Design System (GDS) allows for the generation and exploration of a wide number of design alternatives and for the automation of analysis and optimization processes. Algorithmic Design (AD) tools effectively support the development of GDSs, but they tend to be less appealing for the usage of such systems, as they rely on complex algorithmic descriptions of the design that quickly become overwhelming for less experienced programmers. The usage of GDSs is facilitated by Design Space Exploration Interfaces (DSEIs), which allows users to iteratively explore, visualize, and select design alternatives among the multidimensional design space defined by the GDS. DSEIs promote the collaboration between designers, clients, and end-users, making GDSs more interactive and more accessible. DSEIs rely on graphical user interfaces that relieve users from the burden of dealing with AD programs. The creation of such interfaces can be automated, so that they can be quickly created and modified. Although AD-based DSEIs exist for at least three decades, they have been more intensively researched and commercialized over the past eight years. In this article, existing AD-based DSEIs are reviewed, characterized, and compared according to several criteria, such as: navigation, visualization, search, ranking, grouping, filtering, and selection techniques. From this comparative study, a set of guidelines for the development of DSEIs is proposed.
keywords	Design Space Exploration, Algorithmic Design, Graphical User Interface, Data Visualization
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ijac202220202
id	ijac202220202
authors	Garcia, Sara; António Leitao
year	2022
title	Navigating Design Spaces: Finding Designs, Design Collections, and Design Subspaces
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 2, pp. 176–195
summary	Generative design systems can generate a wide panoply of solutions, from which designers search for those thatbest suit their interests. However, without guidance, this search can be highly inefficient, and many interestingsolutions may remain unexplored. This problem is mitigated with automated exploration methods. Still, the onestypically provided by generative design tools are mostly based on black-box methods that drastically reduce therole of the designer, while more straightforward white-box mechanisms are dispersedly found in specificapplications. This paper proposes the Navigator tool, which gathers a set of white-box mechanisms that automate the generation of default, random, similar and hybrid designs and design subspaces, while also supportingthe generation of design collections. The proposed mechanisms were tested with two generative systems thatcreate, respectively, tower and chair designs. We expect that, by providing understandable mechanisms fornavigating design spaces, designers can become more engaged in the search process
keywords	Generative design, design space exploration, randomness, hybridity, similarity
series	journal
last changed	2024/04/17 14:29

_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
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
doi	https://doi.org/10.52842/conf.ecaade.2022.1.323
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_203
id	ecaade2022_203
authors	Kim, Frederick Chando and Huang, Jeffrey
year	2022
title	Perspectival GAN - Architectural form-making through dimensional transformation
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
doi	https://doi.org/10.52842/conf.ecaade.2022.1.341
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	caadria2022_316
id	caadria2022_316
authors	Ladron de Guevara, Manuel, Schneidman, Alexander, Byrne, Daragh and Krishnamurti, Ramesh
year	2022
title	Design Intents Disentanglement: A Multimodal Approach for Grounding Design Attributes in Objects
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. 333-342
doi	https://doi.org/10.52842/conf.caadria.2022.1.333
summary	Language is ambiguous; many terms and expressions convey the same idea. This is especially true in design fields, where conceptual ideas are generally described by high-level, qualitative attributes, called design intents. Words such as "organic", sequences like "this chair is a mixture between Japanese aesthetics and Scandinavian design" or more complex structures such as "we made the furniture layering materials like a bird weaving its nest‚ represent design intents. Furthermore, most design intents do not have unique visual representations, and are highly entangled within the design artifact, leading to complex relationships between language and images. This paper examines an alternative design scenario based on everyday natural language used by designers, where inputs such as a minimal and sleek looking chair are visually inferred by algorithms that have previously learned complex associations between designs and intents‚vision and language, respectively. We propose a multimodal sequence-to-sequence model which takes in design images and their corresponding descriptions and outputs a probability distribution over regions of the images in which design attributes are grounded. Expectedly, our model can reason and ground objective descriptors such as black or curved. Surprisingly, our model can reason about and ground more complex subjective attributes such as rippled or free, suggesting potential regions where the design object might register such vague descriptions. Link to code: https://github.com/manuelladron/codedBert.git
keywords	Natural Language Processing, Multimodal Machine Learning, Design Intents Disentanglement, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_464
id	caadria2022_464
authors	Liu, Xinyu and van Ameijde, Jeroen
year	2022
title	Data-driven Research on Street Environmental Qualities and Vitality Using GIS Mapping and Machine Learning, a Case Study of Ma On Shan, Hong Kong
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
doi	https://doi.org/10.52842/conf.caadria.2022.1.485
summary	In a post-carbon framework, data-driven methods can be used to assess the environmental quality and sustainability of urban streetscape. Streets are an important part of people's daily lives and provide places for social interaction. Therefore, in this study, the relationship between street quality and street vibrancy is measured using the new town of Ma On Shan, Hong Kong as a study area. Firstly, machine learning was used to identify the physical features of streets through geographic information collection and streetscape image acquisition. Secondly, previous measurement algorithms are combined to calculate the greenness, walkability, safety, imageability, enclosure, and complexity of streets. Thirdly, secondary calculations and visualisations were carried out on a Geographic Information System (GIS) platform to observe the current distribution of street qualities. Finally, the relationship between street quality and vibrancy was analysed using SPSS statistical analysis software. The results show that walkability has a positive effect on street vitality, whereas safety and complexity have a negative effect on street vitality. This study demonstrates how the quantitative assessment of urban street environments can be used as a reference for building a green, low-carbon, healthy, and walkable city.
keywords	Street Quality, Geographic Information Systems, Machine Learning, Image Segmentation, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

For more results click below: