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.
Originalsprache | englisch |
---|---|
Seiten (von - bis) | 337-357 |
Seitenumfang | 21 |
Fachzeitschrift | International Journal of Architectural Computing |
Jahrgang | 21 |
Ausgabenummer | 2 |
Frühes Online-Datum | 31 März 2023 |
DOIs | |
Publikationsstatus | Veröffentlicht - Juni 2023 |
Schlagwörter
- deep learning
- generative methods
- parametric design
- design space
- 3D object generation
- ariational autoencoder
- operative design
- artificial intelligence
- machine learning
- voxels
ASJC Scopus subject areas
- Bauwesen
- Angewandte Informatik
- Computergrafik und computergestütztes Design