基于标记表示的统一矢量户型图生成
Unified Vector Floorplan Generation via Markup Representation
把户型图编码成结构化标记语言后统一为下一词元预测，这种「用单一序列语法统一异构条件」的思路可迁移到布局生成、场景图到图像等需要多条件输入的可控生成任务。
原文依据 casts the entire floorplan generation problem into a next token prediction task
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动住宅户型图生成长期以来是连接建筑学与计算机图形学的核心难题，其目标是让空间设计更高效、更易获得。早期基于约束满足或组合优化的方法虽能保证可行性，却缺乏多样性与灵活性。近期的生成模型取得了有前景的结果，但由于表示方式欠佳，难以泛化到异构的条件任务，例如从场地边界、房间邻接图或部分布局出发的生成。为填补这一空白，我们提出户型图标记语言（Floorplan Markup Language, FML），这是一种在单一结构化语法中编码户型图信息的通用表示，将整个户型图生成问题转化为下一词元预测任务。借助 FML，我们开发了基于 Transformer 的生成模型——户型图标记语言模型（Floorplan Markup Language Model, FMLM），能够在多种条件下生成高保真且功能合理的户型图。在 RPLAN 数据集上的综合实验表明，FMLM 尽管是单一模型，仍超越了此前针对特定任务的最优方法。
英文原文摘要 1170 字符
Automatic residential floorplan generation has long been a central challenge bridging architecture and computer graphics, aiming to make spatial design more efficient and accessible. While early methods based on constraint satisfaction or combinatorial optimization ensure feasibility, they lack diversity and flexibility. Recent generative models achieve promising results but struggle to generalize across heterogeneous conditional tasks, such as generation from site boundaries, room adjacency graphs, or partial layouts, due to their suboptimal representations. To address this gap, we introduce Floorplan Markup Language (FML), a general representation that encodes floorplan information within a single structured grammar, which casts the entire floorplan generation problem into a next token prediction task. Leveraging FML, we develop a transformer-based generative model, Floorplan Markup Language Model (FMLM), capable of producing high-fidelity and functional floorplans under diverse conditions. Comprehensive experiments on the RPLAN dataset demonstrate that FMLM, despite being a single model, surpasses the previous task-specific state-of-the-art methods.