用文字提示生成与内部一致的建筑外立面，保持结构不变
ShellMaker: Language-Guided Exterior Completion under Structural Constraints
- 通过参数化屋顶+语言模型优化提示，实现风格一致的外立面生成
- 在固定墙形和开口条件下，生成带PBR材质的完整外表面网格
- 支持多种输入格式，适合建筑生成与数字孪生场景
尽管室内场景生成已取得进展，但与生成内部一致的建筑外立面仍缺乏研究。现有方法可生成平面布局和墙体结构，但通常停留在结构性外壳阶段，缺少风格一致的外墙与屋顶。外立面补全困难在于：基础轮廓、墙体几何与开洞语义必须保持不变——而无约束生成模型常违反这些限制。我们提出ShellMaker，一种在结构约束下进行语言引导的外立面补全框架。给定建筑骨架与文本风格提示，ShellMaker结合参数化屋顶生成、基于大语言模型的部件感知提示优化、墙屋顶联合材质检索及几何感知组装，生成带PBR材质的完整外表面网格。该框架对格式无关的骨架表示兼容，适用于室内生成器、CityGML与CAD输入，在保持结构一致性的同时，显著提升建筑连贯性，优于检索与无约束生成基线。
原文摘要 · Abstract (English)
Despite advances in indoor scene generation, synthesizing coherent building exteriors consistent with generated interiors remains largely unexplored. Existing methods can generate floor plans and wall layouts but typically stop at a structural shell, lacking stylistically consistent facades and roofs. Completing these exteriors is challenging because the footprint, wall geometry, and opening semantics must remain fixed-constraints that unconstrained generative models often violate. We introduce ShellMaker, a language-guided exterior completion framework that operates under these structural constraints. Given a building scaffold and a text style prompt, ShellMaker generates a complete exterior mesh with PBR materials by combining parametric roof generation, LLM-based part-aware prompt refinement, joint wall-roof material retrieval, and geometry-aware assembly. Operating on a format agnostic scaffold representation, ShellMaker generalizes to indoor generators, CityGML, and CAD inputs, while maintaining structural consistency and improving architectural coherence over retrieval and unconstrained generative baselines. The project page is available at https://ruiqixu37.github.io/ShellMaker_web/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。