CG-Floor：质心引导扩散的大规模平面图生成
CG-Floor: Centroid-Guided Diffusion for Large-Scale Floorplan Generation
用质心热图作为结构化条件引导潜扩散 Transformer 生成非曼哈顿房间形状，这种「语义质心+尺寸热图」的条件编码方式可迁移到室内场景布局、矢量图形生成等需要显式解耦位置与形状的任务。
原文依据 employ a latent diffusion transformer to generate large-scale floorplans featuring non-Manhattan room shapes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大规模平面图生成对虚拟空间规划与建筑仿真至关重要。现有方法虽在生成房间形状简单的小规模平面图上取得了成功，但难以处理大规模平面图中出现的复杂房间连接与不规则房间形状。本文提出 CG-Floor，一种质心引导的分层框架，显式解耦房间位置与形状生成以解决上述问题。我们首先引入尺寸感知的语义质心热图，它由预测的房间质心与尺寸导出，提供一种结构化表示来引导由粗到细的平面图生成器有效生成，同时确保语义对齐。此外，我们训练了一个面向复杂房间形状平面图的矢量量化码本，以捕捉房间形状的多样性，并采用潜扩散 Transformer 生成具有非曼哈顿房间形状的大规模平面图。CG-Floor 在大规模 MSD 数据集上取得最优性能，并支持三维平面图转换与编辑，证明了方法的实用性。代码见 https://cic.tju.edu.cn/faculty/likun/projects/CG-Floor。
英文原文摘要 1248 字符
Large-scale floorplan generation is critical for virtual space planning and architectural simulation. Although existing methods have shown success in generating small-scale floorplans with simple room shapes, they struggle to handle complex room connections and irregular room shapes that arise in large-scale floorplans. In this paper, we propose CG-Floor, a centroid-guided hierarchical framework that explicitly decouples room position and shape generation to address these issues. We first introduce the size-aware semantic centroid heatmap, derived from predicted room centroids and sizes, which provides a structured representation to guide the effective generation of a coarse-to-fine floorplan generator while ensuring semantic alignment. Additionally, we train a vector quantized codebook of floorplans with complex room shapes to capture the diversity of room shapes and employ a latent diffusion transformer to generate large-scale floorplans featuring non-Manhattan room shapes. CG-Floor achieves state-of-the-art performance on the large-scale MSD dataset, and supports 3D floorplan conversion and editing, demonstrating the practicality of our approach. The code is available at https://cic.tju.edu.cn/faculty/likun/projects/CG-Floor.