Floorplan Generation by Alternating Geometry and Semantics Optimization
- 30 March 2026
- journal article
- Published by Wiley in Computer Graphics Forum
Abstract
Creating floorplans lays the foundation for architectural design and scene modeling. We propose a novel framework for generating diverse high‐quality floorplans under predefined constraints. Central to our method is an iterative refinement process for optimizing the bounding boxes of rooms and the floorplan semantics image, which defines a vector floorplan together. Vector floorplans can be generated through a learning‐based refinement process. Our framework supports various constraints, such as floorplan boundaries, topological graphs, and bubble diagrams. Extensive experiments demonstrate that our method is superior to state‐of‐the‐art techniques, particularly in generating a wider variety of solutions that cater to various architectural needs.Keywords
Funding Information
- National Natural Science Foundation of China (62372152)
- Fundamental Research Funds for the Central Universities (PA2025GDSK0035)
This publication has 16 references indexed in Scilit:
- DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis2024
- MaskPLAN: Masked Generative Layout Planning from Partial Input2024
- HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising2023
- LayoutDM: Discrete Diffusion Model for Controllable Layout Generation2023
- ArchiGAN: Artificial Intelligence x Architecture2020
- Intelligent Home 3D: Automatic 3D-House Design From Linguistic Descriptions Only2020
- Floor-SP: Inverse CAD for Floorplans by Sequential Room-Wise Shortest Path2019
- PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows2019
- Raster-to-Vector: Revisiting Floorplan Transformation2017
- Deep Residual Learning for Image Recognition2016