arXiv 2602.071002026-02-06cs.CV

TLC-Plan: 一种基于两级代码库的网络用于端到端向量地板计划生成

TLC-Plan: A Two-Level Codebook Based Network for End-to-End Vector Floorplan Generation

Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology（湖北交通物联网重点实验室，计算机科学与人工智能学院，武汉理工大学）；School of Information Engineering, Nanchang University（信息工程学院，南昌大学）

Biao Xiong, Zhen Peng, Ping Wang, Qiegen Liu, Xian Zhong

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

TLC-Plan通过两级代码库网络直接生成端到端向量地板计划，实现高效且拓扑有效的建筑设计。

摘要：

自动地板计划生成旨在通过联合建模全局空间组织和精确几何细节来提高设计质量、建筑效率和可持续性。然而，现有方法在栅格空间中操作，并依赖于事后向量化，这会引入结构不一致并阻碍端到端学习。受组合空间推理的启发，我们提出了TLC-Plan，一种分层生成模型，可以直接从输入边界合成向量地板计划，与基于模块化和可重用模式的人类建筑工作流程对齐。TLC-Plan采用两级VQ-VAE对全局布局进行编码，作为语义标记的房间边界框，并使用多边形级代码细化局部几何。这种层次结构统一在一个CodeTree表示中，同时一个自回归变压器根据边界采样代码，生成多样化且拓扑有效的设计，而无需显式房间拓扑或尺寸先验。广泛的实验显示，TLC-Plan在RPLAN数据集上实现了最先进的性能（FID = 1.84，MSE = 2.06），并在LIFULL数据集上取得了领先结果。所提出的框架为现实世界建筑应用中的约束意识和可扩展的向量地板计划生成做出了贡献。源代码和训练模型已发布在https://github.com/rosolose/TLC-PLAN。

英文摘要：

Automated floorplan generation aims to improve design quality, architectural efficiency, and sustainability by jointly modeling global spatial organization and precise geometric detail. However, existing approaches operate in raster space and rely on post hoc vectorization, which introduces structural inconsistencies and hinders end-to-end learning. Motivated by compositional spatial reasoning, we propose TLC-Plan, a hierarchical generative model that directly synthesizes vector floorplans from input boundaries, aligning with human architectural workflows based on modular and reusable patterns. TLC-Plan employs a two-level VQ-VAE to encode global layouts as semantically labeled room bounding boxes and to refine local geometries using polygon-level codes. This hierarchy is unified in a CodeTree representation, while an autoregressive transformer samples codes conditioned on the boundary to generate diverse and topologically valid designs, without requiring explicit room topology or dimensional priors. Extensive experiments show state-of-the-art performance on RPLAN dataset (FID = 1.84, MSE = 2.06) and leading results on LIFULL dataset. The proposed framework advances constraint-aware and scalable vector floorplan generation for real-world architectural applications. Source code and trained models are released at https://github.com/rosolose/TLC-PLAN.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。