Floorplan Generation by Alternating Geometry and Semantics Optimization
Computer Graphics Forum · 30.03.2026
DOI: 10.1111/cgf.70370 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 30.03.2026. Verfasst von Wenming Wu und 4 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
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.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Wu, W., Hu, S., Liu, L., Zheng, L., & Fu, X. (2026). Floorplan Generation by Alternating Geometry and Semantics Optimization. Computer Graphics Forum. https://doi.org/10.1111/cgf.70370
Vancouver
Wu W, Hu S, Liu L, Zheng L, Fu X. Floorplan Generation by Alternating Geometry and Semantics Optimization. Computer Graphics Forum. 2026. doi:10.1111/cgf.70370
BibTeX
@article{Wu2026,
author = {Wu, Wenming and Hu, Sizhe and Liu, Ligang and Zheng, Liping and Fu, Xiao‐Ming},
title = {Floorplan Generation by Alternating Geometry and Semantics Optimization},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70370}
}
EUVIMED