魔法城：基于语言的美学自适应城市生成与可控3D资产和布局
MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts
AI总结：
MajutsuCity通过可控3D资产和布局生成逼真城市，结合语言驱动和美学自适应，实现高保真度和风格多样性。
摘要：
生成逼真的3D城市是世界模型、虚拟现实和游戏开发的基础，其中理想的城市场景必须在风格多样性、细粒度和可控性之间取得平衡。然而，现有方法难以在文本生成带来的创造性灵活性与显式结构表示带来的对象级可编辑性之间取得平衡。我们介绍了MajutsuCity，一种基于自然语言和美学自适应的框架，用于合成结构一致且风格多样的3D城市场景。MajutsuCity将城市表示为可控布局、资产和材料的组合，并通过四阶段流程运行。为了在初始生成后扩展可控性，我们进一步集成了MajutsuAgent，一个交互式语言基础编辑代理，支持五种对象级操作。为了支持逼真且可定制的场景合成，我们还构建了MajutsuDataset，一个高质量的多模态数据集，包含2D语义布局和高度图、多样化的3D建筑资产以及精心挑选的PBR材质和天空盒，每项都配有详细的注释。同时，我们开发了一套实用的评估指标，涵盖结构一致性、场景复杂性、材质保真度和光照氛围等关键维度。大量实验表明，MajutsuCity将布局FID降低了83.7%，相比CityDreamer和CityCraft分别降低了20.1%。我们的方法在所有AQS和RDR得分上均排名第一，明显优于现有方法。这些结果证实MajutsuCity在几何保真度、风格适应性和语义可控性方面成为3D城市生成的新状态-of-the-art。我们预计我们的框架可以启发3D城市生成的新研究领域。我们的项目页面：https://longhz140516.github.io/MajutsuCity/。
英文摘要：
Generating realistic 3D cities is fundamental to world models, virtual reality, and game development, where an ideal urban scene must satisfy both stylistic diversity, fine-grained, and controllability. However, existing methods struggle to balance the creative flexibility offered by text-based generation with the object-level editability enabled by explicit structural representations. We introduce MajutsuCity, a natural language-driven and aesthetically adaptive framework for synthesizing structurally consistent and stylistically diverse 3D urban scenes. MajutsuCity represents a city as a composition of controllable layouts, assets, and materials, and operates through a four-stage pipeline. To extend controllability beyond initial generation, we further integrate MajutsuAgent, an interactive language-grounded editing agent} that supports five object-level operations. To support photorealistic and customizable scene synthesis, we also construct MajutsuDataset, a high-quality multimodal dataset} containing 2D semantic layouts and height maps, diverse 3D building assets, and curated PBR materials and skyboxes, each accompanied by detailed annotations. Meanwhile, we develop a practical set of evaluation metrics, covering key dimensions such as structural consistency, scene complexity, material fidelity, and lighting atmosphere. Extensive experiments demonstrate MajutsuCity reduces layout FID by 83.7% compared with CityDreamer and by 20.1% over CityCraft. Our method ranks first across all AQS and RDR scores, outperforming existing methods by a clear margin. These results confirm MajutsuCity as a new state-of-the-art in geometric fidelity, stylistic adaptability, and semantic controllability for 3D city generation. We expect our framework can inspire new avenues of research in 3D city generation. Our project page: https://longhz140516.github.io/MajutsuCity/.
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。
