AI-Driven Design and Generative Architecture

AI-Infused Design - Merging parametric models for architectural design

Adam Sebestyen, Ozan Özdenizci, Robert Legenstein, Urs Hirschberg

Published 2025

Thumbnail for AI-Infused Design - Merging parametric models for architectural design
📄 Paper
This paper presents ongoing work on developing 3D Generative AI tools based on parametric models to facilitate novel types of Design Space Exploration (DSE) to overcome human biases and expand the range of feasible design solutions. By integrating parametric models and neural networks, the study demonstrates how 3D-mesh based datasets generated from different parametric models can be combined in deep learning to create more diverse design spaces. Specifically, we compare training on the same datasets with an unconditioned Variational Autoencoder (VAE) and with conditioned Denoising Diffusion Models (DDMs). We present a novel approach of mixing DDM design spaces and contrast this method with our previous work using a VAE. The paper compares the outputs of VAE and DDMs, highlighting their respective strengths and weaknesses, and proposes a hybrid generative AI model combining both approaches to harness their complementary advantages.

Abstract

This paper presents ongoing work on developing 3D Generative AI tools based on parametric models to facilitate novel types of Design Space Exploration (DSE) to overcome human biases and expand the range of feasible design solutions. By integrating parametric models and neural networks, the study demonstrates how 3D-mesh based datasets generated from different parametric models can be combined in deep learning to create more diverse design spaces. Specifically, we compare training on the same datasets with an unconditioned Variational Autoencoder (VAE) and with conditioned Denoising Diffusion Models (DDMs). We present a novel approach of mixing DDM design spaces and contrast this method with our previous work using a VAE. The paper compares the outputs of VAE and DDMs, highlighting their respective strengths and weaknesses, and proposes a hybrid generative AI model combining both approaches to harness their complementary advantages.

Topics

Form FindingGANsGenerative Design and Design Space ExplorationLLMs for AECParametric, Computational and Algorithmic DesignVAEdesign automationdesign space optimizationdiffusion modelsgeometry generationtext-to-3D

Cite this paper

@inproceedings{a660af06,
title = "AI-Infused Design: Merging parametric models for architectural design",
author = "Adam Sebestyen and Ozan {\"O}zdenizci and Robert Legenstein and Hirschberg, \{Urs Leonhard\}",
year = "2024",
month = sep,
language = "English",
isbn = "978-9-49120-737-2",
volume = "1",
pages = "489–498",
editor = "Kontovourkis, \{ Odysseas\} and Phocas, \{Marios C.\} and Wurzer, \{Gabriel \}",
booktitle = "Data-Driven Intelligence",
publisher = " eCAADe (Education and Research in Computer Aided Architectural Design in Europe)",
note = "42nd eCAADe Conference on Education and research in Computer Aided Architectural Design in Europe. Data-Driven Intelligence : eCAADe 2024, eCAADe 2024 ; Conference date: 09-09-2024 Through 13-09-2024",
url = "https://cyprusconferences.org/ecaade2024/",
address="Europe"
}