Tokenizing Buildings: A Transformer for Layout Synthesis
This addresses layout synthesis for architectural design, representing an incremental advance in applying Transformers to structured domain data.
The paper tackles the problem of layout synthesis in Building Information Modeling by introducing Small Building Model (SBM), a Transformer-based architecture that tokenizes buildings into sequences while preserving compositional structure. The model learns compact room embeddings that cluster by type and topology, enabling strong semantic retrieval, and produces functionally sound layouts with fewer collisions and boundary violations.
We introduce Small Building Model (SBM), a Transformer-based architecture for layout synthesis in Building Information Modeling (BIM) scenes. We address the question of how to tokenize buildings by unifying heterogeneous feature sets of architectural elements into sequences while preserving compositional structure. Such feature sets are represented as a sparse attribute-feature matrix that captures room properties. We then design a unified embedding module that learns joint representations of categorical and possibly correlated continuous feature groups. Lastly, we train a single Transformer backbone in two modes: an encoder-only pathway that yields high-fidelity room embeddings, and an encoder-decoder pipeline for autoregressive prediction of room entities, referred to as Data-Driven Entity Prediction (DDEP). Experiments across retrieval and generative layout synthesis show that SBM learns compact room embeddings that reliably cluster by type and topology, enabling strong semantic retrieval. In DDEP mode, SBM produces functionally sound layouts, with fewer collisions and boundary violations and improved navigability.