SBM tokenizes building rooms via a sparse attribute-feature matrix and trains a Transformer for high-fidelity embeddings plus autoregressive layout generation, yielding better retrieval and fewer layout errors than baselines.
Layoutvlm: Differentiable optimization of 3d layout via vision-language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Tokenizing Buildings: A Transformer for Layout Synthesis
SBM tokenizes building rooms via a sparse attribute-feature matrix and trains a Transformer for high-fidelity embeddings plus autoregressive layout generation, yielding better retrieval and fewer layout errors than baselines.