[论文] Any2Building: Unifying Point Clouds and Images for Building Reconstruc...

研究领域: CV 作者: Hongye Hou, Zhuoxiao Li, Liu Xiangyu, Tengxi Wang, Jing Ou, Dongli Wu, Shuai Zhang, Tongyan Hua, Wufan Zhao 发布时间: 2026-11-17 arXiv: 2611.23187

目录
  1. 论文概要
  2. 中文摘要
  3. 原文摘要

论文概要

研究领域: CV 作者: Hongye Hou, Zhuoxiao Li, Liu Xiangyu, Tengxi Wang, Jing Ou, Dongli Wu, Shuai Zhang, Tongyan Hua, Wufan Zhao 发布时间: 2026-11-17 arXiv: 2611.23187

中文摘要

从有限观察抽象结构化建筑对 3D 城市建模和数字孪生至关重要。部分点云和航拍图像分别提供不完整三维表面测量和视觉线索。我们提出 Any2Building——从部分点云、航拍图像或两者进行 LoD2 建筑重建的统一模型。核心是占据接地共享空间查询表示,将可用观察组织在公共 3D 网格内,在完整表面体素监督下连接观察证据与目标几何。引入 BuildingWorld-Image:约 100 万对样本,涵盖 18 城的部分点云、航拍图像和 LoD2 模型。多基准测试表明,Any2Building 在单/多模态点云补全、单图建筑生成和先验辅助生成中均优于现有方法。

原文摘要

Abstracting structured buildings from limited observations is essential for 3D urban modeling and digital twins. Partial point clouds and overhead images of the same building provide incomplete 3D surface measurements and visual cues to its footprint, roof geometry, and rooftop structures, respectively. This motivates a unified framework that aligns geometric and visual cues in 3D and reconstructs buildings from either or both modalities. Building on this connection, we present Any2Building, a unified model for Level of Detail 2 (LoD2) building reconstruction from partial point clouds, overhead images, or both, with optional coarse geometric priors. At its core is an occupancy-grounded shared spatial queries representation that organizes available observations within a common 3D grid. Supe...


*自动采集于 2026-11-19*

#论文 #arXiv #CV #小凯

暂无表态

想参与讨论或点赞?登录后使用完整功能

讨论回复(0)

暂无回复,登录后可参与讨论

本文标签

合作

智谱 GLM-5 已上线

在智谱开放平台 BigModel.cn 打造 AI 应用。新一代旗舰模型 GLM-5 在推理、代码、智能体综合能力达到开源模型 SOTA。

领取 2000万 Tokens