Pre-training on physically valid but architecturally implausible synthetic floor plans substantially improves cross-domain transfer and data-efficient fine-tuning for conditioned layout generation across two model paradigms and three datasets.
Floor plan recon- struction from sparse views: Combining graph neural network with constrained diffusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Domain Shift in Conditioned Floor Plan Generation: Synthetic Pre-training for Data-Efficient Adaptation
Pre-training on physically valid but architecturally implausible synthetic floor plans substantially improves cross-domain transfer and data-efficient fine-tuning for conditioned layout generation across two model paradigms and three datasets.