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 17619

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

_id	ecaade2024_80
id	ecaade2024_80
authors	Li, Wenpei; Wu, Jiaqian; M. Herr, Christiane; Stouffs, Rudi
year	2024
title	Enhancing Lexicon Based Evaluation of Urban Green Space Characteristics and Perceptions with a Large Language Model
doi	https://doi.org/10.52842/conf.ecaade.2024.2.059
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 59–68
summary	Evaluating Urban green space Characteristics and Human Perceptions (UCHP) is crucial for landscape design and management due to their impact on public health. Online park reviews provide valuable insights into human-environment interactions, enabling the large-scale evaluation of UCHP. However, existing approaches to classify online park reviews commonly ignore text context, leading to low precision of UCHP quantification and supervised approaches are rarely applied due to huge cost. To improve the precision and effectiveness of UCHP quantification, we propose a novel workflow comprising five stages: custom lexicon creation, design of labels for a Large Language Model (LLM), sentence classification using lexicon and LLM, and performance evaluation using a manually annotated dataset and four metrics: precision, recall, accuracy, and F1 score. To examine the performance of the LLM, we compared the classification of 15 UCHP using LLM, lexicon, and lexicon+LLM. The analysis involved utilizing online park review sentences from Google Map and TripAdvisor using the proposed workflow. The higher precision, accuracy and F1 score demonstrate that combination of lexicon and LLM yields the highest performance, followed by using only lexicon and then solely LLM. This performance evaluation demonstrates the validity of the proposed LLM-aided workflow, providing a practical, reliable, and efficient alternative to the lower performance of unsupervised methods, or costly supervised classification methods. We discuss the limitations of lexicon+LLM and outline new opportunities for LLM application in landscape studies.
keywords	urban green space, characteristics and human perceptions, large language model, evaluation
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_273
id	caadria2024_273
authors	Li, Xiaoqian, Han, Zhen, Liu, Gang and Stouffs, Rudi
year	2024
title	A Rapid Prediction Model for View-Based Glare Performance With Multimodal Generative Adversarial Networks
doi	https://doi.org/10.52842/conf.caadria.2024.1.029
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 29–38
summary	Machine learning-based glare prediction has greatly improved the efficiency of performance feedback. However, its limited generalizability and the absence of intuitive predictive indicators have constrained its practical application. In response, this study proposes a prediction model for luminance distribution images based on the multimodal learning approach. This model focuses on objects within the field of view, integrating spatial and material features through images. It also employs semantic feature mapping and multimodal data integration to flexibly represent building information, removing limitations on model validity imposed by changes in design scenarios. Additionally, the study proposes a multimodal Generative Adversarial Network tailored for the multimodal inputs. This network is equipped with unique feature fusion and reinforcement blocks, along with advanced up-sampling techniques, to efficiently distill and extract pertinent information from the inputs. The model's efficacy is verified by cases focusing on residential building luminance distribution, with a 97% improvement in computational speed compared to simulation methods. Offering both speed and accuracy, this model provides designers with a rapid, flexible, and intuitive supporting approach for daylight performance optimization design, particularly beneficial in the early design stage.
keywords	Glare Prediction, Prediction Model, Multimodal Model, Generative Adversarial Networks
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2020_260
id	caadria2020_260
authors	LI, Yan, DU, Hongwu and WANG, Qing
year	2020
title	The Association Study Between Residential Building Interface and Perceived Density based on VR Technology - Taking 2 Enclosed Residential Districts of Guangzhou as Examples
doi	https://doi.org/10.52842/conf.caadria.2020.1.711
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 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 711-720
summary	As urban development enters the stock increment era , the demand of environmental quality in urban residential districts gradually improves, making the construction of livable residential environment an important direction of urban development. The improvement of livable environment is the inevitable result of this process and perceived density is an indispensable and important part. Among the statistical methods, preference study is the most commonly one to explore the subjective factors affecting preference. The experience of immersive virtual environment can provide a more appropriate analytical method better for traditional image selection. Different permeability of architectural interface has significant influences on the perception of space comfortability, crowding and fascination. In this paper, two existing enclosed residential districts are selected for case study. The factors closely related to perceived density, such as solid Wall, grille, glass, open space, greening, etc, are selected by using immersive virtual technology. Through the interviewees' evaluations of perceived density of the virtual environment, the relationship between building interface and the perceived density of the residential area will be established.
keywords	Spatial Perceived Density; Virtual Reality Technology; Enclosed Residential District; Housing Interface; Association Study
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	ecaade2024_210
id	ecaade2024_210
authors	Li, Yangzhi; Fingrut, Adam; Altun, Sevgi
year	2024
title	Embedding Systems Platform Arduino and Robotics into Architectural Education: A project-based approach combining computational design and digital fabrication
doi	https://doi.org/10.52842/conf.ecaade.2024.2.685
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 685–694
summary	This paper investigates integrating robotic fabrication technologies within architectural pedagogy, aiming to develop effective teaching strategy tailored for a diverse group of students, including postgraduate and undergraduate students. Robotics is an essential technology in Industry 4.0, providing a wide range of capabilities in the manufacturing field. The rapid advancement of robotic arms in various industries has opened new possibilities for architectural education. Many architecture schools worldwide have established experimental laboratories equipped with robotic arms, creating opportunities for students to explore beyond the traditional scope of CNC manufacturing. However, professional courses on integrating robotic construction technologies into architectural education are scarce. This research aims to explore using robots as an open interface for problem-solving, geometry exploration, and programming in architectural education, catering to the students' diverse backgrounds and skill levels. By utilizing robotic construction technologies, students can engage in hands-on experimentation, fostering the adoption of digital fabrication techniques.
keywords	Architectural education, Digital Fabrication, Parametric design, Robotic fabrication, Hands-on experimentation
series	eCAADe
email
last changed	2024/11/17 22:05

_id	cf2009_501
id	cf2009_501
authors	Li, Yongzhi; Lertlakkhanakul, Jumphon; Lee, Seongki and Choi, Jinwon
year	2009
title	Design with space syntax analysis based on building information model: Towards an interactive application of building information model in early design process
source	T. Tidafi and T. Dorta (eds) Joining Languages, Cultures and Visions: CAADFutures 2009, PUM, 2009, pp. 501- 514
summary	This paper introduces a new framework to enable user-friendly space syntax analysis during the initial design stage. It assists designers, without in-depth knowledge on space syntax, to evaluate and compare design outcomes rapidly. The framework is realized by integration between space syntax and building information model in which space topology is autonomously retrieved. A BIM modeler so called ‘ArchiSpace’ has been developed to demonstrate the applicability of the framework to design practice. Our experiment shows that designers can use the modeler to analyze their design alternatives instantly at any moment during the initial design stage. Therefore, users can generate and evaluate their design alternatives simultaneously without distraction and tedious work on the space syntax analysis in detail.
keywords	Space syntax, building information modeling, evidence based design, space topology
series	CAAD Futures
email
last changed	2009/06/08 20:53

_id	caadria2023_390
id	caadria2023_390
authors	Li, Yu, Li, Lingling and Yue, Naihua
year	2023
title	A Surrogate-Assisted Optimization Approach to Improve Thermal Comfort and Energy Efficiency of Sports Halls in Subtropical Climates
doi	https://doi.org/10.52842/conf.caadria.2023.1.301
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 301–310
summary	Balancing the thermal comfort and energy efficiency has been recognized as a critical issue in sports hall design, which is yet to be properly implemented in early design stages due to the huge computational cost and delayed simulation feedback. This paper develops an accelerated optimization approach for thermal comfort and energy efficiency of sports halls by combining surrogate modelling with evolutionary algorithms. An integrated computational workflow designated for early-stage application was established that consists of Design of experiments, Surrogate modelling, Surrogate-assisted multi-objective optimization, and Multi-criteria decision making. Specifically, a parametric sports hall model was set up for batch physics-based simulations to generate abundant training samples, which was then utilized to develop surrogate models for the rapid prediction of thermal comfort and energy efficiency. The validated surrogate models were eventually linked with evolutionary algorithms to quickly identify the optimal design solution(s). The performance of the developed approach was evaluated against the traditional simulation-based optimization (SBMOO) method. Results indicated that the proposed approach could save 70.91% of total computational time for this case study, whilst achieving better optimized thermal comfort and energy efficiency with a reduction of mean PMV and site EUI by 0.001 and 1.60 kWh/m2/yr versus the SBMOO method.
keywords	Thermal comfort, Energy efficiency, Multi-objective optimization, Surrogate model, Sports hall
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2023_412
id	caadria2023_412
authors	Li, Yuanyuan, Huang, Chenyu and Yao, Jiawei
year	2023
title	Optimising the Control Strategies for Performance-Driven Dynamic Building Facades Using Machine Learning
doi	https://doi.org/10.52842/conf.caadria.2023.1.199
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 199–208
summary	The balance between energy consumption and indoor environmental comfort is a continuing research topic in building energy efficiency. The dynamic façades (DF) are considered a practical approach to separate the sun and create more shadows for buildings with curtain walls, reducing the HVAC system's energy consumption. However, the design complexity of the DF leads to a time-consuming simulation process, making it difficult to modify the design parameters in the early design stage efficiently. This paper provides optimized control strategies for four dynamic façade prototypes. We use explainable machine learning to explore the relationship between design parameters of DF and indoor performance, including Energy Use Intensity (EUI) and Daylight Glare Probability (DGP). We deployed the trained model in optimizing the rotation angle of DF per hour on a typical day to minimize the EUI and DGP of the target room. The results show that the rotation angle of DF significantly affects the DGP, whereas the room size affects EUI performance more than rotation angles. Optimized control strategies of DF bring a maxim 13.5% EUI decrease and 51.7% reduction of DGP. Our work provides a generalizable design flow for performance-driven dynamic skin design.
keywords	Dynamic façade, Energy consumption, Indoor comfort, computational simulation, Multi-objective optimization, Machine learning
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2022_394
id	caadria2022_394
authors	Li, Yuanyuan, Huang, Chenyu, Zhang, Gengjia and Yao, Jiawei
year	2022
title	Machine Learning Modeling and Genetic Optimization of Adaptive Building Facade Towards the Light Environment
doi	https://doi.org/10.52842/conf.caadria.2022.1.141
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. 141-150
summary	For adaptive facades, the dynamic integration of architectural and environmental information is essential but complex, especially for the performance of indoor light environments. This research proposes a new approach that combines computer-aided design methods and machine learning to enhance the efficiency of this process. The first step is to clarify the design factors of adaptive facade, exploring how parameterized typology models perform in simulation. Then interpretable machine learning is used to explain the contribution of adaptive facade parameters to light criteria (DLA, UDI, DGP) and build prediction models for light simulation. Finally, Wallacei X is used for multi-objective optimization, determines the optimal skin options under the corresponding light environment, and establishes the optimal operation model of the adaptive facades against changes in the light environment. This paper provides a reference for designers to decouple the influence of various factors of adaptive facades on the indoor light environment in the early design stage and carry out more efficient adaptive facades design driven by environmental performance.
keywords	Adaptive Facades, Light Environment, Machine learning, Light Simulation, Genetic Algorithm, SDG 3, SDG 12
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2020_113
id	ecaade2020_113
authors	Li, Yunqin, Yabuki, Nobuyoshi, Fukuda, Tomohiro and Zhang, Jiaxin
year	2020
title	A big data evaluation of urban street walkability using deep learning and environmental sensors - a case study around Osaka University Suita campus
doi	https://doi.org/10.52842/conf.ecaade.2020.2.319
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. 319-328
summary	Although it is widely known that the walkability of urban street plays a vital role in promoting street quality and public health, there is still no consensus on how to measure it quantitatively and comprehensively. Recent emerging deep learning and sensor network has revealed the possibility to overcome the previous limit, thus bringing forward a research paradigm shift. Taking this advantage, this study explores a new approach for urban street walkability measurement. In the experimental study, we capture Street View Picture, traffic flow data, and environmental sensor data covering streets within Osaka University and conduct both physical and perceived walkability evaluation. The result indicates that the street walkability of the campus is significantly higher than that of municipal, and the streets close to large service facilities have better walkability, while others receive lower scores. The difference between physical and perceived walkability indicates the feasibility and limitation of the auto-calculation method.
keywords	walkability; WalkScore; deep learning; Street view picture; environmental sensor
series	eCAADe
email
last changed	2022/06/07 07:51

_id	caadria2019_134
id	caadria2019_134
authors	Li, Yunqin, Zhang, Jiaxin and Yu, Chuanfei
year	2019
title	Intelligent Multi-Objective Optimization Method for Complex Building Layout based on Pedestrian Flow Organization - A case study of People's Court building in Anhui, China
doi	https://doi.org/10.52842/conf.caadria.2019.1.271
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 271-280
summary	The pedestrian flow of the building influences and determines the layout of the building's plan. For buildings with complex flow such as courts, airports, and stations, mixed flow line and low traffic efficiency are prone to be problems. However, the optimization of the layout of complex flow buildings usually relies on the architect's experience to judge and trials to improve. To overcome these problems, we attempt to establish a parametric model of buildings' plan (taking a typical court building as an example) with information about the different pedestrian flow and functional groups. Based on the Rhino and Grasshopper platform, we take the minimum of different pedestrian flow path length and the maximum of total spatial integration value and the minimum of total spatial entropy value as the starting point, combines pathfinding algorithm, Space Syntax and multi-objective genetic algorithm to optimize space allocation. The result shows that, compared with the original scheme, the intelligent optimised scheme can reduce the spatial waste caused by improper flow organisation, effectively improve space transportation capacity and spatial organization efficiency.
keywords	Intelligent optimisation; space allocation; multi-objective optimization algorithm; Space Syntax; pathfinding algorithm
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	acadia22_714
id	acadia22_714
authors	Li, Yunqin; Zhang, Jiaxin; Wang, Xueqiang; Ma, Kai
year	2022
title	Measuring Street Vitality Based on Video-image Using Deep Learning
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. 714-725.
summary	This paper proposes a deep convolutional neural network-based framework for fine-scale studies on automatic evaluation of street-level vitality using multiple object tracking and image segmentation with video data. A deep learning model for street vitality evaluation was proposed based on the intensity and complexity of pedestrian activities.
series	ACADIA
type	paper
email
last changed	2024/02/06 14:04

_id	caadria2023_106
id	caadria2023_106
authors	Li, Yuqian and Xu, Weiguo
year	2023
title	Research on Architectural Sketch to Scheme Image Based on Context Encoder
doi	https://doi.org/10.52842/conf.caadria.2023.1.069
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 69–78
summary	Architects are used to hand drawing sketches to express the architectural creation intention. To present these abstract sketches, architects and teams need to convert sketches into architectural scheme images, which requires a lot of time and labour. Deep learning may have the potential to improve the efficiency of this work. The common sketch-to-image generation is based on Generative Adversarial Network (GAN), and the research of edge-to-image has made a big progress. But these methods require strict alignment of data pairs, which is difficult to achieve. Zhu et al. proposed the loss of Cycle-Consistent, which solved the problem that pairs of data sets are difficult to collect. However, most of the image translation methods require strict alignment between image data pairs, which can be achieved only for the edge mapping extracted from the image; but the sketch is very different from the edge. Due to the abstractness and fuzziness of the sketch, any simple distortion cannot complete the task of providing pixel-level alignment between the sketch and image; And image translation is the transfer of image features such as colour and texture. The original image has a strong constraint on the generated image, which makes the original structure of the image impossible to be changed. By image inpainting, we address this topic using a joint image completion approach with Context-Encoder, where the architectural sketch provides the image context for generating the scheme images. This setting has two advantages: first, the joint images can avoid the complexity of cross modal problems and the strict alignment of the data pairs as image-to-image translation; second, because of the weak constraint, the outputs have greater freedom, which perhaps can generate more imaginative results. The Context-Encoder generates scheme images on the data sets of general architectural sketches. The results present that the applicability of the completion method is better than that of the method of image translation. And scheme images that is different from the original architectural sketch contours have been generated.
keywords	Sketch, Building Scheme Image, Image Completion, Context-Encoder
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2022_523
id	caadria2022_523
authors	Li, Zhixian, Huang, Xiaoran and Ruszczewski, Szymon
year	2022
title	Conflict and Reconciliation Between Architectural Heritage Values and Energy Sustainability, A Case Study of Xidi Village Anhui Province
doi	https://doi.org/10.52842/conf.caadria.2022.1.707
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. 707-716
summary	Virtual reality (VR) can enhance users' spatial perception by enabling spatial design activities. Conversely, the VR environment provides more visual information for the user to process than the desktop environment, resulting in a low efficiency of the design process. This study aims to verify whether VR can have a distinctive influence on the spatial design experience compared to the desktop environment. We conducted user studies on design experience in VR and desktop environments to accomplish this goal. The results revealed that participants‚ satisfaction with the design experience was higher in VR; however, the task completion was more time consuming than in the desktop environment.
keywords	Architectural Heritage, Energy Consumption, Designer‚s Simulation Toolkit, Xidi Village, Huizhou, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ijac20053206
id	ijac20053206
authors	Liakata-Pechlivanidou, Anastasia; Zerefos, Stylianos C.; Zerefos, Stylianos N.
year	2005
title	Perceptual and Cognitive Factors that Influence Orientation in Computer Generated Real Architectural Space
source	International Journal of Architectural Computing vol. 3 - no. 2, 245-254
summary	This study presents results from an experiment that concerns spatial perception and cognition in virtual environments. It also includes the effects of how the development of a simulated virtual space can change perception and cognition of a real building perceived only through architectural drawings and photographs. In the experiment each student was shown external and internal 360° images, representing nodes in virtual space, of the same virtual building. Two different groups of students were formed. The first group was shown photorealistic rendered images, while the other group the same images with non-photorealistic representation. Differences in orientation tendencies of the participating students, as well as statistical results from these experiments were tested and are presented in this paper. It was found that there was a statistically significant tendency of the students towards larger scatter in more luminous virtual space as well as a tendency to visit lit parts of virtual space.
series	journal
more	http://www.multi-science.co.uk/ijac.htm
last changed	2007/03/04 07:08

_id	caadria2024_386
id	caadria2024_386
authors	Liang, Jiadong, Zhong, Ximing and Koh, Immanuel
year	2024
title	Bridging Bim and AI: A Graph-Bim Encoding Approach for Detailed 3D Layout Generation Using Variational Graph Autoencoder
doi	https://doi.org/10.52842/conf.caadria.2024.1.221
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 221–230
summary	Building Information Modelling (BIM) data provides an abundant source with hierarchical and detailed information on architectural elements. Nevertheless, transforming BIM data into an understandable format for AI to learn and generate controllable and detailed three-dimensional (3D) models remains a significant research challenge. This paper explores an encoding approach for converting BIM data into graph-structured data for AI to learn 3D models, which we define as Graph-BIM encoding. We employ the graph reconstruction capabilities of a Variational Graph Autoencoder (VGAE) for the unsupervised learning of BIM data to identify a suitable encoding method. VGAE's graph generation capabilities also reason for spatial layouts. Results demonstrate that VGAE can reconstruct BIM 3D models with high accuracy, and can reason the entire spatial layout from partial layout information detailed with architectural components. The primary contribution of this research is to provide a novel encoding approach for bridging AI and BIM encoding. The Graph-BIM encoding method enables low-cost, self-supervised learning of diverse BIM data, capable of learning and understanding the complex relationships between architectural elements. Graph-BIM provides foundational encoding for training general-purpose AI models for 3D generation.
keywords	BIM, graph-structured, encoding approach, VGAE, graph reconstruction and generation
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_198
id	ecaade2024_198
authors	Liang, Jiadong; Zhong, Ximing; Koh, Immanuel
year	2024
title	Building-VGAE: Generating 3D detailing and layered building models from simple geometry
doi	https://doi.org/10.52842/conf.ecaade.2024.1.625
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 625–634
summary	In the current field of AI-assisted architectural design, deep learning models primarily focus on simulating the highly detailed final models designed by human architects. However, in practical design tasks, the final model demands a high level of detail and clear layered classification information for building components. This presents a more significant challenge. We propose a three-dimensional(3D) building generation framework—Building-VGAE, based on Variational Graph Autoencoder (VGAE). Building-VGAE can generate 3D models with detailed building components and layered structure information from end to end, according to design constraints and building volumes. Building-VGAE’s experiment involves transforming 27,965 Housegan data into 3D data represented as graph-structured. The VGAE model then learns the data features and predicts the building component categories to which nodes and edges belong in the experiment. The results demonstrate that the framework can precisely reconstruct and predict building layouts that comply with design constraints and enable unified editing of building components of the same category. Building-VGAE contributes to its ability to learn the generative relationship from design constraints and building volumes to complex high-detail models compared to existing AI generative models. It also possesses prediction and editing capabilities based on the layered classification information of building components. This framework has the potential to position AI as a design partner for human architects, offering end-to-end 3D generative intelligence.
keywords	Variational Graph Auto-Encoder, 3D Spatial Grid Structure, Detailed Building Components, Layered Structure, Graph Reconstruction and Generation
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2009_074
id	caadria2009_074
authors	Liang, Rung-Huei; Ying-Ming Huang
year	2009
title	Visualizing Bits as Urban Semiotics
doi	https://doi.org/10.52842/conf.caadria.2009.033
source	Proceedings of the 14th International Conference on Computer Aided Architectural Design Research in Asia / Yunlin (Taiwan) 22-25 April 2009, pp. 33-42
summary	Geosemiotics, defined as the study of meaning of placing signs in the material world, concerns the interaction of spatial, individual, social, and cultural contexts. Mobile technology, enabling spatial awareness successfully, has turned our living space into coordinates to broaden geosemiotics study. With interdisciplinary perspectives, there is an emerging potential to integrate the study of mobile spatial interaction and geosemiotics and we address several open issues of geospatial applications in this paper. Since indexicality is the focus of geosemiotics study, we focus on digital indexicalities referring to physical space. Physical indexical signs are usually set by government or organizations rather than individuals, and therefore we propose a new concept to place personal indexical signs in the physical space with mobile devices and augmented reality technology. Overlapped onto the physical world via visual, iconic, and metaphorical methods, what these unique personal semiotics bring is a living space with novel urban landscape and geosemiotics.
keywords	locative media; geosemiotics; augmented reality; ubiquitous computing; mobile spatial interaction
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	698a
authors	Liang, You-Dong and Barsky, Brian A.
year	1983
title	An Analysis and Algorithm for Polygon Clipping
source	Communications of the ACM November, 1983. vol. 26: pp. 868-877 : ill. includes bibliography.
summary	(This is one of the two standard algorithms for clipping. The other is the Sutherland-Hodgman reentrant algorithm). The process of polygon clipping is analyzed and the understanding gained thereby forms the foundation of a very direct algorithm. Each edge of the input polygon is considered to be a vector and is then extended to be a line of infinite extent. The boundary line segments of the clip window are extended in a similar fashion to become boundary lines. The intersection points of an extended edge with the boundary lines are identified as entry or exit points. It is observed that these entry and exit points can be used to characterize the visibility status of the edge. Not only might the edge have a visible segment, but it can also induce the inclusion in the output polygon of a vertex at a corner of the clip window called a turning vertex. To quantify the visibility conditions, the edge is written in parametric form. The possible contributions (including nil) that can be provided to the output polygon by a particular edge are established. This analysis is then embedded in an algorithm. An arbitrary example input polygon is given and the output of the algorithm is shown. The execution time for this example using this algorithm is measured to be half of what is required by the standard Sutherland-Hodgman reentrant polygon clipping algorithm
keywords	polygons, clipping, algorithms, computer graphics
series	CADline
last changed	2003/06/02 13:58

_id	05b4
authors	Liang, You-Dong and Barsky, Brian A.
year	1984
title	A New Concept and Method for Line Clipping
source	ACM Transactions on Graphics. January, 1984. vol. 3: pp. 1-22 : ill. includes bibliography
summary	A new concept and method for line clipping is developed that describes clipping in an exact and mathematical form. The basic ideas form the foundation for a family of algorithms for two-dimensional, three-dimensional, and four-dimensional (homogeneous coordinates) line clipping. The line segment to be clipped is mapped into a parametric representation. From this, a set of conditions is derived that describes the interior of the clipping region. Observing that these conditions are all of similar form, they are rewritten such that the solution to the clipping problem is reduced to a simple max/min expression. For each dimension, the mathematics are discussed, an example is given, the algorithm is designed, and a performance test is conducted. The new algorithm is compared with the traditional Sutherland-Cohen clipping algorithm. Using randomly generated data, the new algorithm showed a 36 percent, 40 percent, and 79 percent improvement for two-dimensional, three-dimensional, and four- dimensional clipping, respectively. One of the advantages of this algorithm is the quick rejection of line segments that are invisible. In addition, this algorithm can be easily generalized for clipping against any convex viewing volume
keywords	algorithms, clipping, computer graphics, analysis
series	CADline
last changed	2003/06/02 13:58

_id	cf2005_2_36_65
id	cf2005_2_36_65
authors	LIAO Kai and HAN Chia Y.
year	2005
title	Collective Pavilions: A Generative Architectural Modelling for Traditional Chinese Pagoda
source	Learning from the Past a Foundation for the Future [Special publication of papers presented at the CAAD futures 2005 conference held at the Vienna University of Technology / ISBN 3-85437-276-0], Vienna (Austria) 20-22 June 2005, pp. 129-138
summary	This paper investigates generative architectural modelling for traditional Chinese architecture and aims to explore and extend the potential of adaptive computing for architectural design methods. The design manners analysis of traditional pagodas architectures is made in a holistic view and under historical perspective. We propose a descriptive model and generative system for the design of traditional Chinese pagodas, by which each pagoda is defined as a collection of style-matched and form-coordinated pavilions and described by both topological graphs and variant geometrical units. Our approach models both of the building geometry and space organization/spatial patterns of pagodas separately. The generative mechanism consists of a framework of grammar-based design and parametric, recursive shape computation. Accordingly, the generative algorithm is also made of two levels, the topology of spatial patterns and the shape geometrical parameters that characterize pavilion variations. The algorithm for computing the former is based on GP (Genetic Programming) and the latter GA (Genetic Algorithms). To explore the collective behaviour of a group of pavilions, multi-agent modelling approach is incorporated in composition patterns search. A prototype system, 'glPagoda', using the OpenGL graphics library for rendering and visualization, has been developed and implemented on PC windows platform.
keywords	pagoda, grammar-based design, multi-agent modelling, generative design system
series	CAAD Futures
email
last changed	2005/05/05 07:06

For more results click below: