Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Zilong, He, Jun, Huang, Xiaobin, Xiong, Ziyi, Luo, Yang, Ye, Junyan, Li, Weijia, Chen, Yiping, Han, Ting
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.20415
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915658724278272
author Huang, Zilong
He, Jun
Huang, Xiaobin
Xiong, Ziyi
Luo, Yang
Ye, Junyan
Li, Weijia
Chen, Yiping
Han, Ting
author_facet Huang, Zilong
He, Jun
Huang, Xiaobin
Xiong, Ziyi
Luo, Yang
Ye, Junyan
Li, Weijia
Chen, Yiping
Han, Ting
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20415
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts
Huang, Zilong
He, Jun
Huang, Xiaobin
Xiong, Ziyi
Luo, Yang
Ye, Junyan
Li, Weijia
Chen, Yiping
Han, Ting
Computer Vision and Pattern Recognition
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/.
title MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20415