Exploring the latent space distribution of a graph autoencoder trained on 3D models of modernist architecture
Saved in:
| Title: | Exploring the latent space distribution of a graph autoencoder trained on 3D models of modernist architecture |
|---|---|
| Authors: | Erik Bauscher, Thomas Wortmann |
| Source: | International Journal of Architectural Computing. 23:742-752 |
| Publisher Information: | SAGE Publications, 2025. |
| Publication Year: | 2025 |
| Description: | Building on previous research in generative graph machine learning in architecture, this paper investigates how data generation and preparation can change the distribution of a model’s latent space and thus its generative qualities. Therefore, we first present and discuss our previous approach of applying generative graph machine learning in architecture by sampling the latent space of a graph autoencoder trained with the augmentations of four examples of modernist buildings. We then present a new method of data generation for modernist buildings in the style of architect Mies van der Rohe, which produces a large range of 3D building models with great geometric variety. Trained on the new dataset, the graph autoencoder shows a more continuous latent space, confirmed by visual comparison and by three spatial analysis algorithms that quantitatively assess the spatial structure of the different latent spaces. |
| Document Type: | Article |
| Language: | English |
| ISSN: | 2048-3988 1478-0771 |
| DOI: | 10.1177/14780771251353797 |
| Rights: | CC BY NC |
| Accession Number: | edsair.doi...........c3971b186e0e3960fdd9f37321d9899f |
| Database: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | Building on previous research in generative graph machine learning in architecture, this paper investigates how data generation and preparation can change the distribution of a model’s latent space and thus its generative qualities. Therefore, we first present and discuss our previous approach of applying generative graph machine learning in architecture by sampling the latent space of a graph autoencoder trained with the augmentations of four examples of modernist buildings. We then present a new method of data generation for modernist buildings in the style of architect Mies van der Rohe, which produces a large range of 3D building models with great geometric variety. Trained on the new dataset, the graph autoencoder shows a more continuous latent space, confirmed by visual comparison and by three spatial analysis algorithms that quantitatively assess the spatial structure of the different latent spaces. |
|---|---|
| ISSN: | 20483988 14780771 |
| DOI: | 10.1177/14780771251353797 |