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 609

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

_id	ijac202119106
id	ijac202119106
authors	Del Campo, Matias; Alexandra Carlson, and Sandra Manninger
year	2021
title	Towards Hallucinating Machines - Designing with Computational Vision
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 1, 88–103
summary	There are particular similarities in how machines learn about the nature of their environment, and how humans learn to process visual stimuli. Machine Learning (ML), more specifically Deep Neural network algorithms rely on expansive image databases and various training methods (supervised, unsupervised) to “make sense” out of the content of an image. Take for example how students of architecture learn to differentiate various architectural styles. Whether this be to differentiate between Gothic, Baroque or Modern Architecture, students are exposed to hundreds, or even thousands of images of the respective styles, while being trained by faculty to be able to differentiate between those styles. A reversal of the process, striving to produce imagery, instead of reading it and understanding its content, allows machine vision techniques to be utilized as a design methodology that profoundly interrogates aspects of agency and authorship in the presence of Artificial Intelligence in architecture design. This notion forms part of a larger conversation on the nature of human ingenuity operating within a posthuman design ecology. The inherent ability of Neural Networks to process large databases opens up the opportunity to sift through the enormous repositories of imagery generated by the architecture discipline through the ages in order to find novel and bespoke solutions to architectural problems. This article strives to demystify the romantic idea of individual artistic design choices in architecture by providing a glimpse under the hood of the inner workings of Neural Network processes, and thus the extent of their ability to inform architectural design.The approach takes cues from the language and methods employed by experts in Deep Learning such as Hallucinations, Dreaming, Style Transfer and Vision. The presented approach is the base for an in-depth exploration of its meaning as a cultural technique within the discipline. Culture in the extent of this article pertains to ideas such as the differentiation between symbolic and material cultures, in which symbols are defined as the common denominator of a specific group of people.1 The understanding and exchange of symbolic values is inherently connected to language and code, which ultimately form the ingrained texture of any form of coded environment, including the coded structure of Neural Networks.A first proof of concept project was devised by the authors in the form of the Robot Garden. What makes the Robot Garden a distinctively novel project is the motion from a purely two dimensional approach to designing with the aid of Neural Networks, to the exploration of 2D to 3D Neural Style Transfer methods in the design process.
keywords	Artificial intelligence, design agency, neural networks, machine learning, machine vision
series	journal
email
last changed	2021/06/03 23:29

_id	caadria2021_052
id	caadria2021_052
authors	Yousif, Shermeen and Bolojan, Daniel
year	2021
title	Deep-Performance - Incorporating Deep Learning for Automating Building Performance Simulation in Generative Systems
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. 151-160
doi	https://doi.org/10.52842/conf.caadria.2021.1.151
summary	In this study, we introduce a newly developed method called Deep-Performance, to enable automatic environmental performance simulation prediction without the need to perform simulations, by integrating deep learning strategies. The aim is to train neural networks on datasets with thousands of building design samples and their corresponding performance simulation. The trained model would offer performance prediction for design options emerging in generative protocols. The research is a work-in-progress within a broader project aimed at automating buildings environmental performance evaluations of daylight analysis and energy simulation, using deep learning (DL) models. This paper focuses on the implementation of a supervised DL method for automating the retrieval of daylight analysis metrics, targeting successful daylight design and higher building enclosure efficiency. We have further improved a Pix2Pix model trained on 5 different datasets, each containing 6000 paired images of architectural floor plans and their daylight simulation metrics. In the inference phase, the model was able to accurately predict the daylight simulation for unseen sets of floor plans. For validation, two quantitative assessment metrics were followed to assess the predicted daylight performance against the daylight performance simulation. Both assessment metrics showed high accuracy levels.
keywords	Deep Learning; Artificial Intelligence; Deep-Performance; Automating Building Performance Simulation; Generative Systems
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaade2021_291
id	ecaade2021_291
authors	Mondal, Joy
year	2021
title	Differences between Architects' and Non-architects' Visual Perception of Originality of Tower Typology - Quantification of subjective evaluation using Deep Learning
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 65-74
doi	https://doi.org/10.52842/conf.ecaade.2021.1.065
summary	The paper presents a computational methodology to quantify the differences in visual perception of originality of the rotating tower typology between architects and non-architects. A parametric definition of the Absolute Tower Building D with twelve variables is used to generate 250 design variants. Subsequently, sixty architects and sixty non-architects were asked to rate the design variants, in comparison to the original design, on a Likert scale of 'Plagiarised' to 'Original'. With the crowd-sourced evaluation data, two neural networks - one each for architects and non-architects - were trained to predict the originality score of 15,000 design variants. The results indicate that architects are more lenient at seeing design variants as original. The average originality score by architects is 27.74% higher than the average originality score by non-architects. Compared to a non-architect, an architect is 1.93 times likelier to see a design variant as original. In 92.01% of the cases, architects' originality score is higher than non-architects'. The methodology can be used to capture and predict any subjective opinion.
keywords	Originality; Visual perception; Crowd-sourced; Subjective evaluation; Deep learning; Neural network
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2021_039
id	caadria2021_039
authors	Chen, Jielin, Stouffs, Rudi and Biljecki, Filip
year	2021
title	Hierarchical (multi-label) architectural image recognition and classification
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. 161-170
doi	https://doi.org/10.52842/conf.caadria.2021.1.161
summary	The task of architectural image recognition for both architectural functionality and style remains an open challenge. In addition, the paucity of well-organized, large-scale architectural image datasets with specific consideration for the domain of architectural design research has hindered the exploration of these challenging tasks. Drawing upon images from the professional architectural website ArchdailyÂ®, and leveraging state-of-the-art deep-learning-based classification models, we explore a hierarchical multi-label classification model as a potential baseline for the task of architectural image classification. The resulting model showcases the potential for innovative architectural discipline-related analyses and demonstrates some heuristic insights for visual feature extraction pertaining to both architectural functionality and architectural style.
keywords	image recognition; hierarchical classification; multi-label classification; architectural functionality; style
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2021_389
id	caadria2021_389
authors	del Campo, Matias
year	2021
title	Architecture,Language and AI - Language,Attentional Generative Adversarial Networks (AttnGAN) and Architecture Design
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. 211-220
doi	https://doi.org/10.52842/conf.caadria.2021.1.211
summary	The motivation to explore Attentional Generative Adversarial Networks (AttnGAN) as a design technique in architecture can be found in the desire to interrogate an alternative design methodology that does not rely on images as starting point for architecture design, but language. Traditionally architecture design relies on visual language to initiate a design process, wither this be a napkin sketch or a quick doodle in a 3D modeling environment. AttnGAN explores the information space present in programmatic needs, expressed in written form, and transforms them into a visual output. The key results of this research are shown in this paper with a proof-of-concept project: the competition entry for the 24 Highschool in Shenzhen, China. This award-winning project demonstrated the ability of GraphCNN to serve as a successful design methodology for a complex architecture program. In the area of Neural Architecture, this technique allows to interrogate shape through language. An alternative design method that creates its own unique sensibility.
keywords	Artificial Intelligence; Machine Learning; Artificial Neural Networks; Semiotics; Design Methodology
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	cdrf2021_242
id	cdrf2021_242
authors	Waishan Qiu , Wenjing Li, Xun Liu, and Xiaokai Huang
year	2021
title	Subjectively Measured Streetscape Qualities for Shanghai with Large-Scale Application of Computer Vision and Machine Learning
source	Proceedings of the 2021 DigitalFUTURES The 3rd International Conference on Computational Design and Robotic Fabrication (CDRF 2021)
doi	https://doi.org/https://doi.org/10.1007/978-981-16-5983-6_23
summary	Recently, many new studies emerged to apply computer vision (CV) to street view imagery (SVI) dataset to objectively extract the view indices of various streetscape features such as trees to proxy urban scene qualities. However, human perceptions (e.g., imageability) have a subtle relationship to visual elements which cannot be fully captured using view indices. Conversely, subjective measures using survey and interview data explain more human behaviors. However, the effectiveness of integrating subjective measures with SVI dataset has been less discussed. To address this, we integrated crowdsourcing, CV, and machine learning (ML) to subjectively measure four important perceptions suggested by classical urban design theory. We first collected experts’ rating on sample SVIs regarding the four qualities which became the training labels. CV segmentation was applied to SVI samples extracting streetscape view indices as the explanatory variables. We then trained ML models and achieved high accuracy in predicting the scores. We found a strong correlation between predicted complexity score and the density of urban amenities and services Point of Interests (POI), which validates the effectiveness of subjective measures. In addition, to test the generalizability of the proposed framework as well as to inform urban renewal strategies, we compared the measured qualities in Pudong to other five renowned urban cores worldwide. Rather than predicting perceptual scores directly from generic image features using convolution neural network, our approach follows what urban design theory suggested and confirms various streetscape features affecting multi-dimensional human perceptions. Therefore, its result provides more interpretable and actionable implications for policymakers and city planners.
series	cdrf
last changed	2022/09/29 07:53

_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	sigradi2021_200
id	sigradi2021_200
authors	Karabagli, Kaan, Koc, Mustafa, Basu, Prithwish and As, Imdat
year	2021
title	A Machine Learning Approach to Translate Graph Representations into Conceptual Massing Models
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. 191–202
summary	Machine learning (ML) has popular applications in domains involving image, video, text and voice. However, in architecture, image-based ML systems face challenges capturing the complexity of three-dimensional space. In this paper, we leverage a graph-based ML system that can capture the inherent topology of architectural conceptual designs and identify high-performing latent patterns within such designs. In particular, our goal is to translate architectural graph data into three-dimensional massing models. We are building on our prior ML work, where we, a. discovered latent topological features, b. composed building blocks into new designs, c. evaluated their feasibility, and d. explored Generative Adversarial (Neural) Networks (GAN)-generated design variations. We trained the ML system with architectural design data that we gathered from an online architectural design competition platform, translated them into machine-readable graph representations, and identified their essential subgraphs to develop novel compositions. In this paper, we explore how these novel designs (outputted in graph form), can be translated into three-dimensional architectural form. We present an ML approach to turn graph representations into functional volumetric massing models. The ultimate goal of the study is to develop an end-to-end pipeline to generate architectural design - from a graph representation to a fully developed conceptual proxy of a designed product. The research question is promising in automating conceptual design, and we believe the outcome can be relevant to other design disciplines as well.
keywords	Architectural design, machine learning, conceptual design, deep learning, artificial intelligence
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	acadia21_512
id	acadia21_512
authors	Liu, Zidong
year	2021
title	Topological Networks Using a Sequential Method
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 512-519.
doi	https://doi.org/10.52842/conf.acadia.2021.512
summary	The paper shares preliminary results of a novel sequential method to expand existing topology-based generative design. The approach is applied to building an interactive community design system based on a mobile interface. In the process of building an interactive design system, one of the core problems is to harness the complex topological network formed by user demands. After decades of graph theory research in architecture, a consensus on self-organized complex networks has emerged. However, how to convert input complex topological data into spatial layouts in generative designs is still a difficult problem worth exploring. The paper proposes a way to simplify the problem: in some cases, the spatial network of buildings can be approximated as a collection of sequences based on circulation analysis. In the process of network serialization, the personalized user demands are transformed into activity patterns and further into serial spaces. This network operation gives architects more room to play with their work. Rather than just designing an algorithm that directly translates users’ demands into shape, architects can be more actively involved in organizing spatial networks by setting up a catalogue of activity patterns of the residents, thus contributing to a certain balance of top-down order and bottom-up richness in the project. The research on data serialization lays a solid foundation for the future exploration of Recurrent Neural Network (RNN) applied to generative design.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2021_247
id	ecaade2021_247
authors	Wibranek, Bastian, Liu, Yuxi, Funk, Niklas, Belousov, Boris, Peters, Jan and Tessmann, Oliver
year	2021
title	Reinforcement Learning for Sequential Assembly of SL-Blocks - Self-interlocking combinatorial design based on Machine Learning
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 27-36
doi	https://doi.org/10.52842/conf.ecaade.2021.1.027
summary	Adaptive reconfigurable structures are seen as the next big step in the evolution of architecture. However, to achieve this vision, new tools are required that enable autonomous configuration of given elements based on a specified design objective. Various approaches have been considered in the past, ranging from rule-based methods to evolutionary optimization. Although successful in applications where search heuristics or informative objective functions can be provided, these methods struggle with long-term planning problems. In this paper, we tackle the problem of sequential assembly of SL-blocks which has the character of a combinatorial optimization problem. We explore the applicability of deep reinforcement learning algorithms that recently showed great success on combinatorial problems in other domains, such as board games and molecular design. We highlight the unique challenges presented by the architectural design setting and compare the performance to evolutionary computation and heuristic search baselines.
keywords	Reinforcement Learning; Architectural Assembly; Discrete Design; SL-blocks; Dry Joined
series	eCAADe
email
last changed	2022/06/07 07:57

_id	caadria2021_166
id	caadria2021_166
authors	Hu, Wei
year	2021
title	The experiment of neural network on the cognition of style
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 61-70
doi	https://doi.org/10.52842/conf.caadria.2021.2.061
summary	This paper introduces a method to obtain quantified style description vector which is for computer analysis input by using image style classification task. In the experiment, 3331 architectural photos of three styles obtained by crawling and filtering were used as training data. A deep convolutional neural network was trained to map architectural images to high-dimensional feature space, and then the high-dimensional style description vector was used to output the measurement results of style cognition with fully connected neural network. Tested by test data-set of 371 architectural pictures, the accuracy rate of style cognition reached more than 80%. The neural network using architectural data training was applied to the style cognition of non-architectural objects, high accuracy rate was also achieved, it proved that this quantified style description vector did include the information about style cognition to some extent instead of simply classification. Finally, the similarities and differences between the cognitive characteristics of style of neural network and human beings are investigated.
keywords	deep neural network; style cognition experiment; eye tracker
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	ijac202119205
id	ijac202119205
authors	Fukuda, Tomohiro; Marcos Novak, Hiroyuki Fujii, Yoann Pencreach
year	2021
title	Virtual reality rendering methods for training deep learning, analysing landscapes, and preventing virtual reality sickness
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 2, 190–207
summary	Virtual reality (VR) has been proposed for various purposes such as design studies, presentation, simulation and communication in the field of computer-aided architectural design. This paper explores new roles for VR; in particular, we propose rendering methods that consist of post-processing rendering, segmentation rendering and shadow-casting rendering for more-versatile approaches in the use of data. We focus on the creation of a dataset of annotated images, composed of paired foreground-background and semantic-relevant images, in addition to traditional immersive rendering for training deep learning neural networks and analysing landscapes. We also develop a camera velocity rendering method using a customised segmentation rendering technique that calculates the linear and angular velocities of the virtual camera within the VR space at each frame and overlays a colour on the screen according to the velocity value. Using this velocity information, developers of VR applications can improve the animation path within the VR space and prevent VR sickness. We successfully applied the developed methods to urban design and a design project for a building complex. In conclusion, the proposed method was evaluated to be both feasible and effective.
keywords	Virtual reality, rendering, shader, deep learning, landscape analytics, virtual reality sickness, Fourth Industrial Revolution, computer-aided architectural design
series	journal
email
last changed	2024/04/17 14:29

_id	ecaade2021_158
id	ecaade2021_158
authors	Joyce, Sam Conrad and Nazim, Ibrahim
year	2021
title	Limits to Applied ML in Planning and Architecture - Understanding and defining extents and capabilities
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 243-252
doi	https://doi.org/10.52842/conf.ecaade.2021.1.243
summary	There has been an exponential increase in Machine Learning (ML) research in design. Specifically, with Deep Learning becoming more accessible, frameworks like Generative Adversarial Networks (GANs), which are able to synthesise novel images are being used in the classification and generation of designs in architecture. While much of these explorations successfully demonstrate the 'magic' and potential of these techniques, their limits remain unclear, with only a few, but crucial, discussions on underlying fundamental limits and sensitivities of ML. This is a gap in our understanding of these tools especially within the complex context of planning and architecture. This paper seeks to discuss what limits ML in design as it exists today, by examining the state-of-the-art and mechanics of ML models relevant to design tasks. Aiming to help researchers to focus on productive uses of ML and avoid areas of over-promise.
keywords	Machine Learning; Artificial Intelligence; Creativity
series	eCAADe
email
last changed	2022/06/07 07:52

_id	caadria2021_305
id	caadria2021_305
authors	Keshavarzi, Mohammad, Afolabi, Oladapo, Caldas, Luisa, Yang, Allen Y. and Zakhor, Avideh
year	2021
title	GenScan: A Generative Method for Populating Parametric 3D Scan Datasets
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. 91-100
doi	https://doi.org/10.52842/conf.caadria.2021.1.091
summary	The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce GenScan, a generative system that populates synthetic 3D scan datasets in a parametric fashion. The system takes an existing captured 3D scan as an input and outputs alternative variations of the building layout including walls, doors, and furniture with corresponding textures. GenScan is fully automated system that can also be manually controlled by a user through an assigned user interface. Our proposed system utilizes a combination of a hybrid deep neural network and a parametrizer module to extract and transform elements of a given 3D scan. GenScan takes advantage of style transfer techniques to generate new textures for the generated scenes. We believe our system would facilitate data augmentation to expand the currently limited 3D geometry datasets commonly used in 3D computer vision, generative design and general 3D deep learning tasks.
keywords	Computational Geometry; Generative Modeling; 3D Manipulation; Texture Synthesis
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaade2021_037
id	ecaade2021_037
authors	Kikuchi, Takuya, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2021
title	Automatic Diminished Reality-Based Virtual Demolition Method using Semantic Segmentation and Generative Adversarial Network for Landscape Assessment
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 529-538
doi	https://doi.org/10.52842/conf.ecaade.2021.2.529
summary	In redevelopment projects in mature cities, it is important to visualize the future landscape. Diminished reality (DR) based methods have been proposed to represent the future landscape after the structures are removed. However, two issues remain to be addressed in previous studies. (1) the user needs to prepare 3D models of the structure to be removed and the background structure to be rendered after removal as preprocessing, and (2) the user needs to specify the structure to be removed in advance. In this study, we propose a DR method that detects the objects to be removed using semantic segmentation and completes the removal area using generative adversarial networks. With this method, virtual removal can be performed without preparing 3D models in advance and without specifying the removal target in advance. A prototype system was used for verification, and it was confirmed that the method can represent the future landscape after removal and can run at an average speed of about 8.75 fps.
keywords	landscape visualization; virtual demolition; diminished reality (DR); deep learning; generative adversarial network (GAN); semantic segmentation
series	eCAADe
email
last changed	2022/06/07 07:52

_id	caadria2021_196
id	caadria2021_196
authors	Lu, Yueheng, Tian, Runjia, Li, Ao, Wang, Xiaoshi and Jose Luis, Garcia del Castillo Lopez
year	2021
title	CubiGraph5K - Organizational Graph Generation for Structured Architectural Floor Plan Dataset
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. 81-90
doi	https://doi.org/10.52842/conf.caadria.2021.1.081
summary	In this paper, a novel synthetic workflow is presented for procedural generation of room relation graphs of floor plans from structured architectural datasets. Different from classical floor plan generation models, which are based on strong heuristics or low-level pixel operations, our method relies on parsing vectorized floor plans to generate their intended organizational graph for further graph-based deep learning. This research work presents the schema for the organizational graphs, describes the generation algorithms, and analyzes its time/space complexity. As a demonstration, a new dataset called CubiGraph5K is presented. This dataset is a collection of graph representations generated by the proposed algorithms, using the floor plans in the popular CubiCasa5K dataset as inputs. The aim of this contribution is to provide a matching dataset that could be used to train neural networks on enhanced floor plan parsing, analysis and generation in future research.
keywords	Graph Theory; Algorithm; Architecture Design Dataset; Organizational Graph
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2021_051
id	caadria2021_051
authors	Wu, Shaoji
year	2021
title	Hyperlinking Mechanisms in Commercial Complex - An Example of The Spatial Network in Taikoo Li Sanlitun,Beijing
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 509-518
doi	https://doi.org/10.52842/conf.caadria.2021.2.509
summary	Commercial complexes play an important role in contemporary cities, with elevators, escalators, and other paths on which people do not take natural movement in it. We consider them as spatial hyperlinking paths, which is originated from the webs hyperlinking technology. This paper studies the path network system in Taikoo Li, Sanlitun, Beijing, in three steps. Firstly, The path system is transformed into a network model, and its spatial network distribution is characterized using betweenness centrality. Secondly, a deep learning approach is used to measure the peoples flow at the selected 102 observation points. Then a multiple linear regression(MLR) analysis is conducted using the flow data as dependent variable. And there are 7 independent variables in three types, including betweenness centrality C, H1 and H2 that related to spatial hyperlinks, and B1, F1, F2, and F3 that related to floors. Thirdly, analyzing the MLR model.There are two conclusions. First, using multiple independent variables is better than one variable to fit the peoples flow distribution using the regression model. Second, escalators have the effect of enhancing peoples flow, while elevators have the opposite effect.
keywords	Spatial Hyperlink; 3D spatial networks; Commercial Complex
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2021_080
id	caadria2021_080
authors	Yang, Xuyou and Xu, Weishun
year	2021
title	A Tool for Searching Active Bending Bamboo Strips in Construction via Deep Learning
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. 463-472
doi	https://doi.org/10.52842/conf.caadria.2021.1.463
summary	As an alternative material for construction, the structural use of bamboo in architecture is commonly associated with active bending. However, as natural material, the deformation of unprocessed bamboo strips is affected by the distribution of nodes, whose impact on deformation is difficult to precisely programme for each individual case and thus often causes discrepancies between generic digital simulation and construction. This research proposes a tool for searching active bending bamboo strips via deep leaning based on a multi-task neural network. The tool is able to predict both the number and locations of nodes suggested on bamboo strips according to a target curve as tool input. By approximating the prediction, users can find a strip that is most likely to deform into the desired geometry.
keywords	neural network; active bending; neural architecture search (NAS); bamboo; material behaviour
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	cdrf2021_26
id	cdrf2021_26
authors	Yuqian Li and Weiguo Xu
year	2021
title	Using CycleGAN to Achieve the Sketch Recognition Process of Sketch-Based Modeling
source	Proceedings of the 2021 DigitalFUTURES The 3rd International Conference on Computational Design and Robotic Fabrication (CDRF 2021)
doi	https://doi.org/https://doi.org/10.1007/978-981-16-5983-6_3
summary	Architects usually design ideation and conception by hand-sketching. Sketching is a direct expression of the architect’s creativity. But 2D sketches are often vague, intentional and even ambiguous. In the research of sketch-based modeling, it is the most difficult part to make the computer to recognize the sketches. Because of the development of artificial intelligence, especially deep learning technology, Convolutional Neural Networks (CNNs) have shown obvious advantages in the field of extracting features and matching, and Generative Adversarial Neural Networks (GANs) have made great breakthroughs in the field of architectural generation which make the image-to-image translation become more and more popular. As the building images are gradually developed from the original sketches, in this research, we try to develop a system from the sketches to the images of buildings using CycleGAN algorithm. The experiment demonstrates that this method could achieve the mapping process from the sketches to images, and the results show that the sketches’ features could be recognised in the process.By the learning and training process of the sketches’ reconstruction, the features of the images are also mapped to the sketches, which strengthen the architectural relationship in the sketch, so that the original sketch can gradually approach the building images, and then it is possible to achieve the sketch-based modeling technology.
series	cdrf
email
last changed	2022/09/29 07:53

_id	caadria2021_161
id	caadria2021_161
authors	Zhao, Xin, Han, Yunsong and Shen, Linhai
year	2021
title	Multi-objective Optimisation of a Free-form Building Shape to improve the Solar Energy Utilisation Potential using Artificial Neural Networks
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. 221-230
doi	https://doi.org/10.52842/conf.caadria.2021.1.221
summary	Optimisation of free-form building design is more challenging in terms of building information modelling and performance evaluation compared to conventional buildings. The paper provides a Photogrammetry-based BIM Modelling - Machine Learning Modelling - Multi-objective Optimisation framework to improve the solar energy utilisation potential of free-form buildings. Low altitude photogrammetry is used to collect the building and site environmental information. An ANN prediction model is developed using the control point coordinates and simulation data. Through parametric programming, the multi-objective algorithm is coupled with the ANN model to obtain the trade-off optimal building form. The results show that the maximum solar radiation value in winter can increase by 30.60% and the minimum solar radiation in summer can decrease by 13.99%. It is also shown that the integration of ANN modelling and photogrammetry-based BIM modelling into the multi-objective optimisation method can accelerate the optimisation process.
keywords	Multi-objective optimisation; Artificial neural network; Free-form shape building ; Solar energy utilisation
series	CAADRIA
email
last changed	2022/06/07 07:57

For more results click below: