<div class="csl-bib-body">
<div class="csl-entry">Sebestyen, A., Hirschberg, U., & Rasoulzadeh, S. (2023). Using deep learning to generate design spaces for architecture. <i>International Journal of Architectural Computing</i>, <i>21</i>(2), 337–357. https://doi.org/10.1177/14780771231168232</div>
</div>
-
dc.identifier.issn
1478-0771
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/190980
-
dc.description.abstract
We present an early prototype of a design system that uses Deep Learning methodology—Conditional Variational Autoencoders (CVAE)—to arrive at custom design spaces that can be interactively explored using semantic labels. Our work is closely tied to principles of parametric design. We use parametric models to create the dataset needed to train the neural network, thus tackling the problem of lacking 3D datasets needed for deep learning. We propose that the CVAE functions as a parametric tool in itself: The solution space is larger and more diverse than the combined solution spaces of all parametric models used for training. We showcase multiple methods on how this solution space can be navigated and explored, supporting explorations such as object morphing, object addition, and rudimentary 3D style transfer. As a test case, we implemented some examples of the geometric taxonomy of “Operative Design” by Di Mari and Yoo.
en
dc.language.iso
en
-
dc.publisher
Sage Publications
-
dc.relation.ispartof
International Journal of Architectural Computing
-
dc.subject
3D object generation
en
dc.subject
artificial intelligence
en
dc.subject
deep learning
en
dc.subject
design space
en
dc.subject
generative methods
en
dc.subject
machine learning
en
dc.subject
operative design
en
dc.subject
parametric design
en
dc.subject
variational autoencoder
en
dc.subject
voxels
en
dc.title
Using deep learning to generate design spaces for architecture