FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction
This work addresses the need for incremental floor plan generation tools in architectural design practice, though it appears to be an incremental adaptation of autoregressive methods to a new domain.
The paper tackles the problem of floor plan generation by proposing a multimodal approach that predicts rooms sequentially, addressing the incompatibility of existing end-to-end models with real-world architectural workflows. Experimental results show FPDS achieves competitive performance compared to diffusion models and Tell2Design in text-to-floorplan tasks.
In the architectural design process, floor plan generation is inherently progressive and iterative. However, existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a single pass. This paradigm is often incompatible with the incremental workflows observed in real-world architectural practice. To address this issue, we draw inspiration from the autoregressive 'next token prediction' mechanism commonly used in large language models, and propose a novel 'next room prediction' paradigm tailored to architectural floor plan modeling. Experimental evaluation indicates that FPDS demonstrates competitive performance in comparison to diffusion models and Tell2Design in the text-to-floorplan task, indicating its potential applicability in supporting future intelligent architectural design.