Search papers, labs, and topics across Lattice.
This paper introduces GRE-Diff, a diffusion-based framework that automates the generation and editing of apartment floor plans while adhering to user-defined constraints. By leveraging Gaussian Room Embeddings (GRE) to represent room layouts as spatial Gaussian distributions, the system allows for interactive design through both LLM-parsed instructions and GUI-based inputs. Extensive evaluations on the RPLAN dataset demonstrate that GRE-Diff effectively produces high-quality, constraint-aware designs that enhance the collaboration between AI automation and human creativity in spatial design tasks.
GRE-Diff enables users to create and refine apartment layouts interactively, merging AI efficiency with human creativity in unprecedented ways.
Designing functional and aesthetically coherent floor plans requires exploring a vast space of possible room arrangements, a task that quickly becomes overwhelming for human designers. In this paper, we propose GRE-Diff, a controllable and interactive diffusion-based framework that automates the creation and editing of apartment floor plans under user-specified constraints. By combining AI-generated suggestions with real-time, human-in-the-loop editing, the system enables users to specify room types, room counts, boundary shapes, and editing operations through LLM-parsed instructions or GUI-based interaction. It then generates a diverse set of plausible and well-structured designs for refinement. At the core of our approach is Gaussian Room Embedding (GRE), a continuous latent representation that models each room as a spatial Gaussian distribution capturing its location and extent. Extensive experiments on the RPLAN dataset show that GRE-Diff produces high-quality, constraint-aware, and editable polygonal layouts, offering a practical step toward bridging AI-driven automation and human creativity in spatial design.
