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
id caadria2024_128
authors Bauscher, Erik, Dai, Anni, Elshani, Diellza and Wortmann, Thomas
year 2024
title Learning and Generating Spatial Concepts of Modernist Architecture via Graph Machine Learning
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. 159–168
doi https://doi.org/10.52842/conf.caadria.2024.1.159
summary This project showcases a use case away from most other research in the field of generative AI in architecture. We present a workflow to generate new, three-dimensional spatial configurations of buildings by sampling the latent space of a graph auto-encoder. Graph representations of three-dimensional buildings can store more data and hence reduce the loss of information from building to machine learning model compared to image- and voxel-based representations. Graphs do not only represent information about elements (nodes/pixels/etc.) but also the relationships between elements (edges). This is specifically helpful in architecture where we define space as an assemblage of physical elements which are all somehow connected (i.e., wall touches floor). Our method generates valuable, logical and original geometries that represent the architectural style chosen in the training data. These geometries are highly different from any image-based generation process and justify the importance of graph-based 3D geometry generation of architecture via machine learning. The method also introduces a novel conversion process from architecture to graph, an adapted decoder architecture, and a physical prototype to control the generation process, all making generative machine learning more applicable to a real-world scenario of designing a building.
keywords generative 3D architecture, generative graph machine learning, graph-based architecture, human-computer interaction, graph autoencoder, latentwalk
series CAADRIA
email
full text file.pdf (1,518,534 bytes)
references Content-type: text/plain
Details Citation Select
100%; open Alexander, C. (1977) Find in CUMINCAD A Pattern Language , Oxford University Press

100%; open Alymani, A., Jabi, W., & Corcoran, P. (2022) Find in CUMINCAD Graph machine learning classification using architectural 3D topological models , SIMULATION: Transactions of The Society for Modeling and Simulation International, Online, 1-15. https://doi.org/10.1177/00375497221105894

100%; open Beetz, J., Leeuwen, J. van, & Vries, B. de. (2009) Find in CUMINCAD IfcOWL: A case of transforming EXPRESS schemas into ontologies , AI EDAM, 23(1), 89-101. https://doi.org/10.1017/S0890060409000122

100%; open Carpo, M. (2017) Find in CUMINCAD The Second Digital Turn , MIT Press. https://mitpress.mit.edu/9780262534024/the-second-digital-turn/

100%; open de las Heras, L.-P., Terrades, O. R., Robles, S., & Sanchez, G. (2015) Find in CUMINCAD CVC-FP and SGT: A new database for structural floor plan analysis and its groundtruthing tool , International Journal on Document Analysis and Recognition (IJDAR), 18(1), 15-30. https://doi.org/10.1007/s10032-014-0236-5

100%; open del Campo, M. (2022) Find in CUMINCAD Deep House-Datasets, estrangement, and the problem of the new , Architectural Intelligence, 1(1), 12. https://doi.org/10.1007/s44223-022-00013-w

100%; open Elshani, D., Hernandez, D., Lombardi, A., Siriwardena, L., Schwinn, T., Fisher, A., Staab, S., Menges, A., & Wortmann, T. (2023) Find in CUMINCAD Building Information Validation and Reasoning Using Semantic Web Technologies , M. Turrin, C. Andriotis, & A. Rafiee (Eds.), Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries (pp. 470-484). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-37189-9_31

100%; open Elshani, D., Lombardi, A., Fisher, A., Hernandez, D., Staab, S., & Wortmann, T. (2022) Find in CUMINCAD Knowledge Graphs for Multidisciplinary Co-Design: Introducing RDF to BHoM , ESWC - LDAC 2022

100%; open Hamilton, W. L. (2020) Find in CUMINCAD Fast Graph Representation Learning with PyTorch Geometric , Morgan and Claypool Publishers

100%; open Hillier, B. (1996) Find in CUMINCAD Inductive Representation Learning on Large Graphs , Cambridge University Press

100%; open Hu, R., Huang, Z., Tang, Y., van Kaick, O., Zhang, H., & Huang, H. (2020) Find in CUMINCAD Graph2Plan: Learning Floorplan Generation from Layout Graphs , ACM Transactions on Graphics, 39(4). https://doi.org/10.1145/3386569.3392391

100%; open Koh, I. (2020) Find in CUMINCAD CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis (arXiv:1904 , Springer

100%; open McGlinn, K., & Pauwels, P. (Eds.). (2022) Find in CUMINCAD Buildings and Semantics: Data Models and Web Technologies for the Built Environment , CRC Press. https://doi.org/10.1201/9781003204381

100%; open Mitchell, M. (2020) Find in CUMINCAD Artificial intelligence-A guide for thinking humans , Penguin Books

100%; open Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Köpf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Chintala, S. (2019) Find in CUMINCAD PyTorch: An Imperative Style , High-Performance Deep Learning Library (arXiv:191201703). arXiv. https://doi.org/10.48550/arXiv.1912.01703

100%; open Rasmussen, M. H., Lefrançois, M., Schneider, G., & Pauwels, P. (2020) Find in CUMINCAD BOT: The Building Topology Ontology of the W3C Linked Building Data Group , Semantic Web. https://doi.org/10.3233/SW-200385

100%; open Wu, W., Xiao-Ming, F., Tang, R., Wang, Y., Qi, Y.-H., & Liu, L. (2019) Find in CUMINCAD Neurosymbolic AI -- Why, What, and How , ACM Transactions on Graphics, 38, 234:1-234:12. https://doi.org/10.1145/3355089.3356556

100%; open Zhong, X., Koh, I., & Fricker, P. D. P. (2023) Find in CUMINCAD Building-GNN: Exploring a co-design framework for generating controllable 3D building prototypes by graph and recurrent neural networks , Digital Design Reconsidered: Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023), 431-440. https://doi.org/10.52842/conf.ecaade.2023.2.431

last changed 2024/11/17 22:05
pick and add to favorite papersHOMELOGIN (you are user _anon_822775 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002