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 2464

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

_id	caadria2014_184
id	caadria2014_184
authors	Janssen, Patrick and Vignesh Kaushik
year	2014
title	Plot Packing
doi	https://doi.org/10.52842/conf.caadria.2014.533
source	Rethinking Comprehensive Design: Speculative Counterculture, Proceedings of the 19th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2014) / Kyoto 14-16 May 2014, pp. 533–542
summary	Generative design tools can accelerate the optioneering process by allowing designers to quickly generate large numbers of design variants, thereby enabling a wider and more thorough exploration to be conducted. This paper focuses on procedures for generating inner city street networks and city block massing studies for sites within existing urban areas. A novel procedure is proposed that is capable of subdividing complex non-orthogonal sites into similarly sized well-formed plots and subsequently further subdividing these plots into sizes appropriate for selected city block typologies. The application of the procedure is demonstrated on a site in Singapore.
keywords	Urban optioneering; street networks; parametric urbanism; quadrilateral mesh generation
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	cdrf2023_273
id	cdrf2023_273
authors	Pixin Gong, Xiaoran Huang, Chenyu Huang, Shiliang Wang
year	2023
title	Modeling on Outdoor Thermal Comfort in Traditional Residential Neighborhoods in Beijing Based on GAN
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_23
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
summary	With the support of new urban science and technology, the bottom-up and human-centered space quality research has become the key to delicacy urban governance, of which the Universal Thermal Climate Index (UTCI) have a severe influence. However, in the studies of actual UTCI, datasets are mostly obtained from on-site measurement data or simulation data, which is costly and ineffective. So, how to efficiently and rapidly conduct a large-scale and fine-grained outdoor environmental comfort evaluation based on the outdoor environment is the problem to be solved in this study. Compared to the conventional qualitative analysis methods, the rapidly developing algorithm-supported data acquisition and machine learning modelling are more efficient and accurate. Goodfellow proposed Generative Adversarial Nets (GANs) in 2014, which can successfully be applied to image generation with insufficient training data. In this paper, we propose an approach based on a generative adversarial network (GAN) to predict UTCI in traditional blocks. 36000 data samples were obtained from the simulations, to train a pix2pix model based on the TensorFlow framework. After more than 300 thousand iterations, the model gradually converges, where the loss of the function gradually decreases with the increase of the number of iterations. Overall, the model has been able to understand the overall semantic information behind the UTCI graphs to a high degree. Study in this paper deeply integrates the method of data augmentation based on GAN and machine learning modeling, which can be integrated into the workflow of detailed urban design and sustainable construction in the future.
series	cdrf
email
last changed	2024/05/29 14:04

_id	acadia14_43
id	acadia14_43
authors	Puusepp, Renee
year	2014
title	Agent-based models for computing circulation
doi	https://doi.org/10.52842/conf.acadia.2014.043
source	ACADIA 14: Design Agency [Proceedings of the 34th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 9781926724478]Los Angeles 23-25 October, 2014), pp. 43-52
summary	This paper presents and compares two computational models for designing circulation networks in settlements.
keywords	Multi Agent Systems in Design, Generative Design, Circulation Diagrams
series	ACADIA
type	Normal Paper
email
last changed	2022/06/07 08:00

_id	sigradi2014_345
id	sigradi2014_345
authors	Shiordia Lopez, Rodrigo; Dr. David Jason Gerber
year	2014
title	Context-Aware Multi-Agent Systems: Negotiating Intensive Fields
source	SIGraDi 2014 [Proceedings of the 18th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-9974-99-655-7] Uruguay- Montevideo 12,13,14 November 2014, pp. 138-143
summary	This paper presents research into a technique using context-aware agent based branching L-systems to design explore an urban development scheme in an area of peripheral Mexico City. The design research demonstrates a viable approach to engaging design with specific agent driven objectives that negotiate across highly differentiated fields of data sets. These data sets are the driving force behind this technique, to generate highly differentiated infrastructure and urban networks that are simulated to be autonomous and emergent. The described system consists of simulated robotic autonomous agents that sample and negotiate across data from the site, and react to differences in order to deploy an irrigation network for a polluted and highly saline former lake-bed east of Mexico City.
keywords	Multi-Agent Systems; L-Systems; Generative Urban Design; Multi-Objective Optimization: Design Agency
series	SIGRADI
email
last changed	2016/03/10 10:00

_id	acadia14projects_139
id	acadia14projects_139
authors	Shiordia, Rodrigo; Gerber, David Jason
year	2014
title	Context-Aware Multi-Agent Systems: Negotiating Intensive Fields
doi	https://doi.org/10.52842/conf.acadia.2014.139
source	ACADIA 14: Design Agency [Projects of the 34th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 9789126724478]Los Angeles 23-25 October, 2014), pp. 139-142
summary	This poster presents an implementation of a context aware L-System for simulating a generative method for deploying irrigation networks in a brownfield in Mexico City. A custom system was designed with the constraints that a discrete data sensing logic imposes on a generative strategy based on a scheme responding to soil salinity.
keywords	Multi-Agent Systems in Design, Generative Design, Big Data, Robotics and Autonomous Design Systems, Collective Intelligence in Design, L-System
series	ACADIA
type	Research Projects
email
last changed	2022/06/07 07:56

_id	ascaad2021_093
id	ascaad2021_093
authors	Alani, Mostafa; Bilal Al-Kaseem
year	2021
title	Fill in the Blanks: Deep Convolutional Generative Adversarial Networks to Investigate the Virtual Design Space of Historical Islamic Patterns
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 614-621
summary	This paper presents a method to explore the virtual design space of historical Islamic Geometric Patterns (IGP). The introduced approach utilizes Deep Convolutional Generative Adversarial Network (DCGAN) to learn from historically existing hexagonal-based IGP to synthesis novel, authentically looking Geometric Patterns.
series	ASCAAD
email
last changed	2021/08/09 13:13

_id	acadia20_228
id	acadia20_228
authors	Alawadhi, Mohammad; Yan, Wei
year	2020
title	BIM Hyperreality
doi	https://doi.org/10.52842/conf.acadia.2020.1.228
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 228-236.
summary	Deep learning is expected to offer new opportunities and a new paradigm for the field of architecture. One such opportunity is teaching neural networks to visually understand architectural elements from the built environment. However, the availability of large training datasets is one of the biggest limitations of neural networks. Also, the vast majority of training data for visual recognition tasks is annotated by humans. In order to resolve this bottleneck, we present a concept of a hybrid system—using both building information modeling (BIM) and hyperrealistic (photorealistic) rendering—to synthesize datasets for training a neural network for building object recognition in photos. For generating our training dataset, BIMrAI, we used an existing BIM model and a corresponding photorealistically rendered model of the same building. We created methods for using renderings to train a deep learning model, trained a generative adversarial network (GAN) model using these methods, and tested the output model on real-world photos. For the specific case study presented in this paper, our results show that a neural network trained with synthetic data (i.e., photorealistic renderings and BIM-based semantic labels) can be used to identify building objects from photos without using photos in the training data. Future work can enhance the presented methods using available BIM models and renderings for more generalized mapping and description of photographed built environments.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaadesigradi2019_605
id	ecaadesigradi2019_605
authors	Andrade Zandavali, Bárbara and Jiménez García, Manuel
year	2019
title	Automated Brick Pattern Generator for Robotic Assembly using Machine Learning and Images
doi	https://doi.org/10.52842/conf.ecaade.2019.3.217
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 3, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 217-226
summary	Brickwork is the oldest construction method still in use. Digital technologies, in turn, enabled new methods of representation and automation for bricklaying. While automation explored different approaches, representation was limited to declarative methods, as parametric filling algorithms. Alternatively, this work proposes a framework for automated brickwork using a machine learning model based on image-to-image translation (Conditional Generative Adversarial Networks). The framework consists of creating a dataset, training a model for each bond, and converting the output images into vectorial data for robotic assembly. Criteria such as: reaching wall boundary accuracy, avoidance of unsupported bricks, and brick's position accuracy were individually evaluated for each bond. The results demonstrate that the proposed framework fulfils boundary filling and respects overall bonding structural rules. Size accuracy demonstrated inferior performance for the scale tested. The association of this method with 'self-calibrating' robots could overcome this problem and be easily implemented for on-site.
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:54

_id	ijac201816406
id	ijac201816406
authors	As, Imdat; Siddharth Pal and Prithwish Basu
year	2018
title	Artificial intelligence in architecture: Generating conceptual design via deep learning
source	International Journal of Architectural Computing vol. 16 - no. 4, 306-327
summary	Artificial intelligence, and in particular machine learning, is a fast-emerging field. Research on artificial intelligence focuses mainly on image-, text- and voice-based applications, leading to breakthrough developments in self-driving cars, voice recognition algorithms and recommendation systems. In this article, we present the research of an alternative graph- based machine learning system that deals with three-dimensional space, which is more structured and combinatorial than images, text or voice. Specifically, we present a function-driven deep learning approach to generate conceptual design. We trained and used deep neural networks to evaluate existing designs encoded as graphs, extract significant building blocks as subgraphs and merge them into new compositions. Finally, we explored the application of generative adversarial networks to generate entirely new and unique designs.
keywords	Architectural design, conceptual design, deep learning, artificial intelligence, generative design
series	journal
email
last changed	2019/08/07 14:04

_id	sigradi2020_60
id	sigradi2020_60
authors	Asmar, Karen El; Sareen, Harpreet
year	2020
title	Machinic Interpolations: A GAN Pipeline for Integrating Lateral Thinking in Computational Tools of Architecture
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 60-66
summary	In this paper, we discuss a new tool pipeline that aims to re-integrate lateral thinking strategies in computational tools of architecture. We present a 4-step AI-driven pipeline, based on Generative Adversarial Networks (GANs), that draws from the ability to access the latent space of a machine and use this space as a digital design environment. We demonstrate examples of navigating in this space using vector arithmetic and interpolations as a method to generate a series of images that are then translated to 3D voxel structures. Through a gallery of forms, we show how this series of techniques could result in unexpected spaces and outputs beyond what could be produced by human capability alone.
keywords	Latent space, GANs, Lateral thinking, Computational tools, Artificial intelligence
series	SIGraDi
email
last changed	2021/07/16 11:48

_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	ecaade2023_125
id	ecaade2023_125
authors	Baºarir, Lale, Çiçek, Selen and Koç, Mustafa
year	2023
title	Demystifying the patterns of local knowledge: The implicit relation of local music and vernacular architecture
doi	https://doi.org/10.52842/conf.ecaade.2023.2.791
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 791–800
summary	As the zeitgeist suggests, the development of novel design output using Artificial Neural Networks (ANNs) is becoming an important milestone in the architectural design discourse. With the recent encounter of the computational design realm with the diffusion models, it becomes even easier to generate 2D and 3D design outputs. Yet, the utilization of machine learning tools within design computing domains is confined to generating or classifying visual and encoded data. However, it is critical to evaluate the untapped potentials of machine learning technologies in terms of illuminating the implicit correlations and links underlying distinct concepts and themes across a wide range of technical domains. With the ongoing research project named “Local Intelligence", we hypothesized that the local knowledge of a certain location might be conceptualized as a distributed network to connect different forms of local knowledge. As the first case of the project, we tried to reinstate a commonality between the local music and vernacular architecture, for which we trained generative adversarial network (GAN) models with the visual spectrograms translated from the audio data of the local songs and images of vernacular architectural instances from a defined geography. The two multi-modal GAN models differ in terms of the inherent convolutional layers and data pairing process. The outcomes demonstrated that both GAN models can learn how to depict vernacular architectural features from the rhythmic pattern of the songs in various patterns. Consequently, the implicit relations between music and architecture in the initial findings come one step closer to being demystified. Thus, the process and generative outcomes of the two models are compared and discussed in terms of the legibility of the architectural features, by taking the original vernacular architectural image dataset as the ground truth.
keywords	Local Intelligence, Machine Learning, Generative Adversarial Network (GAN), Local Music, Vernacular Architecture
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ascaad2021_022
id	ascaad2021_022
authors	Baºarir, Lale; Kutluhan Erol
year	2021
title	Briefing AI: From Architectural Design Brief Texts to Architectural Design Sketches
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 23-31
summary	The main focus of this research is to uncover the underlying intuitive knowledge of architecture with the help of machine learning models. To achieve this, a generic architectural design process is considered and divided into iterative portions based on their output for each phase. This study looks into the initial portion of the architectural design process called “Briefing”. The authors search for the intuition that exists within the design process and how it can be learned by artificial intelligence (AI) that is currently gained through master-apprentice relationship and experience that builds up this knowledge. In this study, a way to enable users to attain an architectural design sketch while defining an architectural design problem with text is explored. This on-going research decomposes the components of the briefing and preliminary design sketching processes. Therefore the domain knowledge at each phase is considered for translating to constraints via natural language processing (NLP) and machine learning (ML) models such as Generative Adversarial Networks (GANs).
series	ASCAAD
type	normal paper
email
last changed	2021/08/09 13:11

_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

_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
doi	https://doi.org/10.52842/conf.caadria.2022.1.353
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
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	caadria2021_225
id	caadria2021_225
authors	Cao, Shuqi and Ji, Guohua
year	2021
title	Automatically generating layouts of large-scale office park using position-based dynamics
doi	https://doi.org/10.52842/conf.caadria.2021.1.021
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 21-30
summary	In this paper we propose an automatic layout algorithm using PBD (Position-Based Dynamic) for large-scale office park planning. Typically, the organization of buildings into a layout is a labor-intensive problem, and takes up most of designers working time. Unlike Evolutionary Algorithms who has high computational cost, and GAN (Generative Adversarial Networks) whose constraints are not explicit, PBD can handle complex geometric constraints fast enough to be used in interactive environments. The high efficiency will not only accelerate the design iteration from draft to drawings, but also provide precious feasible sample for performance optimization. Furthermore, PBD is intuitive and flexible to be implemented which makes it a potential technique to be used in real design workflow.
keywords	Generative Design; Automated Layout Generation; Position-Based Dynamics; Real-time Design Tool; Exploratory Design
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	sigradi2021_114
id	sigradi2021_114
authors	Cesar Rodrigues, Ricardo, Kenzo Imagawa, Marcelo, Rubio Koga, Renan and Bertola Duarte, Rovenir
year	2021
title	Big Data vs Smart Data on the Generation of Floor Plans with Deep Learning
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 217–228
summary	Due to the progressive growth of data dimensionality, addressing how much data and time is required to train deep learning models has become an important research topic. Thus, in this paper, we present a benchmark for generating floor plans with Conditional Generative Adversarial Networks in which we compare 10 trained models on a dataset of 80.000 samples, the models use different data dimensions and hyper-parameters on the training phase, beyond this objective, we also tested the capability of Convolutional Neural Networks (CNN) to reduce the dataset noise. The models' assessment was made on more than 6 million with the Frétche Inception Distance (FID). The results show that such models can rapidly achieve similar or even better FID results if trained with 800 images of 512x512 pixels, in comparison to high dimensional datasets of 256x256 pixels, however, using CNNs to enhance data consistency reproduced optimal results using around 27.000 images.
keywords	Floor plans, Generative design, Generative adversarial networks, Smart Data, Dataset reduction.
series	SIGraDi
email
last changed	2022/05/23 12:10

_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	ecaade2020_017
id	ecaade2020_017
authors	Chan, Yick Hin Edwin and Spaeth, A. Benjamin
year	2020
title	Architectural Visualisation with Conditional Generative Adversarial Networks (cGAN). - What machines read in architectural sketches.
doi	https://doi.org/10.52842/conf.ecaade.2020.2.299
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 299-308
summary	As a form of visual reasoning, sketching is a human cognitive activity instrumental to architectural design. In the process of sketching, abstract sketches invoke new mental imageries and subsequently lead to new sketches. This iterative transformation is repeated until the final design emerges. Artificial Intelligence and Deep Neural Networks have been developed to imitate human cognitive processes. Amongst these networks, the Conditional Generative Adversarial Network (cGAN) has been developed for image-to-image translation and is able to generate realistic images from abstract sketches. To mimic the cyclic process of abstracting and imaging in architectural concept design, a Cyclic-cGAN that consists of two cGANs is proposed in this paper. The first cGAN transforms sketches to images, while the second from images to sketches. The training of the Cyclic-cGAN is presented and its performance illustrated by using two sketches from well-known architects, and two from architecture students. The results show that the proposed Cyclic-cGAN can emulate architects' mode of visual reasoning through sketching. This novel approach of utilising deep neural networks may open the door for further development of Artificial Intelligence in assisting architects in conceptual design.
keywords	visual cognition; design computation; machine learning; artificial intelligence
series	eCAADe
email
last changed	2022/06/07 07:55

_id	caadria2020_446
id	caadria2020_446
authors	Cho, Dahngyu, Kim, Jinsung, Shin, Eunseo, Choi, Jungsik and Lee, Jin-Kook
year	2020
title	Recognizing Architectural Objects in Floor-plan Drawings Using Deep-learning Style-transfer Algorithms
doi	https://doi.org/10.52842/conf.caadria.2020.2.717
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 717-725
summary	This paper describes an approach of recognizing floor plans by assorting essential objects of the plan using deep-learning based style transfer algorithms. Previously, the recognition of floor plans in the design and remodeling phase was labor-intensive, requiring expert-dependent and manual interpretation. For a computer to take in the imaged architectural plan information, the symbols in the plan must be understood. However, the computer has difficulty in extracting information directly from the preexisting plans due to the different conditions of the plans. The goal is to change the preexisting plans to an integrated format to improve the readability by transferring their style into a comprehensible way using Conditional Generative Adversarial Networks (cGAN). About 100-floor plans were used for the dataset which was previously constructed by the Ministry of Land, Infrastructure, and Transport of Korea. The proposed approach has such two steps: (1) to define the important objects contained in the floor plan which needs to be extracted and (2) to use the defined objects as training input data for the cGAN style transfer model. In this paper, wall, door, and window objects were selected as the target for extraction. The preexisting floor plans would be segmented into each part, altered into a consistent format which would then contribute to automatically extracting information for further utilization.
keywords	Architectural objects; floor plan recognition; deep-learning; style-transfer
series	CAADRIA
email
last changed	2022/06/07 07:56

For more results click below: