Saved in:
Bibliographic Details
Main Authors: Niu, Mengyuan, Zhuo, Xinxin, Wang, Ruizhe, Huang, Yuyue, Yang, Junyan, Wang, Qiao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.23804
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915520014450688
author Niu, Mengyuan
Zhuo, Xinxin
Wang, Ruizhe
Huang, Yuyue
Yang, Junyan
Wang, Qiao
author_facet Niu, Mengyuan
Zhuo, Xinxin
Wang, Ruizhe
Huang, Yuyue
Yang, Junyan
Wang, Qiao
contents Urban modeling is essential for city planning, scene synthesis, and gaming. Existing image-based methods generate diverse layouts but often lack geometric continuity and scalability, while graph-based methods capture structural relations yet overlook parcel semantics. We present a controllable framework for large-scale 3D vector urban layout generation, conditioned on both geometry and semantics. By fusing geometric and semantic attributes, introducing edge weights, and embedding building height in the graph, our method extends 2D layouts to realistic 3D structures. It also enables users to directly control the output by modifying semantic attributes. Experiments show that it produces valid, large-scale urban models, offering an effective tool for data-driven planning and design.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23804
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Controllable Generation of Large-Scale 3D Urban Layouts with Semantic and Structural Guidance
Niu, Mengyuan
Zhuo, Xinxin
Wang, Ruizhe
Huang, Yuyue
Yang, Junyan
Wang, Qiao
Computer Vision and Pattern Recognition
Urban modeling is essential for city planning, scene synthesis, and gaming. Existing image-based methods generate diverse layouts but often lack geometric continuity and scalability, while graph-based methods capture structural relations yet overlook parcel semantics. We present a controllable framework for large-scale 3D vector urban layout generation, conditioned on both geometry and semantics. By fusing geometric and semantic attributes, introducing edge weights, and embedding building height in the graph, our method extends 2D layouts to realistic 3D structures. It also enables users to directly control the output by modifying semantic attributes. Experiments show that it produces valid, large-scale urban models, offering an effective tool for data-driven planning and design.
title Controllable Generation of Large-Scale 3D Urban Layouts with Semantic and Structural Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23804