Automating Computational Design with Generative AI

Joern Ploennigs, Markus Berger
7/5/2023
cs.LGcs.AI

Official code: AI4SC/bim-diffusion-models (6 stars, MIT, last commit 2024-05-02).

Abstract

AI image generators based on diffusion models have recently garnered attention for their capability to create images from simple text prompts. However, for practical use in civil engineering they need to be able to create specific construction plans for given constraints. This paper investigates the potential of current AI generators in addressing such challenges, specifically for the creation of simple floor plans. We explain how the underlying diffusion-models work and propose novel refinement approaches to improve semantic encoding and generation quality. In several experiments we show that we can improve validity of generated floor plans from 6% to 90%. Based on these results we derive future research challenges considering building information modelling. With this we provide: (i) evaluation of current generative AIs; (ii) propose improved refinement approaches; (iii) evaluate them on various examples; (iv) derive future directions for diffusion models in civil engineering.

View on arXivView PDF

Code Implementations(1)

AI4SC/bim-diffusion-modelsOfficial100%
MIT

A procedural generation algorithm to generate floor plans for diffusion model training.

60PythonMar 16, 20232 years agoMIT

Similar Papers

Generative AI Models for Different Steps in Architectural Design: A Literature Review

85% match2024

Generative AIBIM: An automatic and intelligent structural design pipeline integrating BIM and generative AI

84% match1 repo272023

UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Models

82% match2024

HouseTune: Two-Stage Floorplan Generation with LLM Assistance

81% match2024

Sketch-Based Facade Renovation With Generative AI: A Streamlined Framework for Bypassing As-Built Modelling in Industrial Adaptive Reuse

80% match2026

Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation

80% match2025

Cite this paper

@article{ploennigs2023automating,
  title  = {Automating Computational Design with Generative AI},
  author = {Joern Ploennigs and Markus Berger},
  year   = {2023},
  eprint = {2307.02511},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.02511v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.02511.svg)](https://codeofpaper.com/paper/2307.02511)

Discussion