Cons2Plan: Vector Floorplan Generation from Various Conditions via a Learning Framework based on Conditional Diffusion Models

作者：Shibo Hong, Xuhong Zhang, Tianyu Du, Cheng Sheng, Xun Wang, Jianwei Yin · 年份：2024 · DOI：10.1145/3664647.3680681 · 被引用次数：5 · 研究领域：Advanced Numerical Analysis Techniques、Infrastructure Maintenance and Monitoring、Handwritten Text Recognition Techniques

The field of floorplan generation has attracted significant interest from the community. Remarkably, recent advances in generative models have markedly enhanced the development of this field. However, generating floorplans that satisfy various conditions remains a challenging task. This paper proposes a learning framework, named Cons2Plan, for automatically and high-quality generating vector floorplans from various conditions. The input conditions can be graphs, boundaries, or a combination of both. The conditional diffusion model is the core component of our Cons2Plan. The denoising network uses a conditional embedding module to incorporate the conditions during the reverse process. Additionally, Cons2Plan incorporates a two-stage approach that generates graph conditions based on boundaries. It uses three networks for node prediction and a novel conditional edge generation diffusion model, named CEDM, for edge generation. We conduct qualitative evaluations, quantitative comparisons, and ablation studies to show that our method produces better floorplans than state-of-the-art methods.