您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Research on 3D Reconstruction Methods for Incomplete Building Point Clouds Using Deep Learning and Geometric Primitives

文献类型： 外文期刊

作者： Ding, Ziqi 1 ; Lu, Yuefeng 1 ; Shao, Shiwei 4 ; Qin, Yong 1 ; Lu, Miao 3 ; Song, Zhenqi 1 ; Sun, Dengkuo 1 ;

作者机构： 1.Shandong Univ Technol, Sch Civil Engn & Geomat, Zibo 255049, Peoples R China

2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China

3.Natl Ctr Technol Innovat Comprehens Utilizat Salin, Dongying 257347, Peoples R China

4.Wuhan Open Univ, Wuhan Vocat Coll Software & Engn, Wuhan 430205, Peoples R China

5.Hubei Engn Res Ctr Intelligent Detect & Identifica, Wuhan 430205, Peoples R China

6.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, State Key Lab Efficient Utilizat Arid & Semiarid A, Beijing 100081, Peoples R China

关键词： three-dimensional reconstruction; point cloud processing; deep learning; point cloud completion

期刊名称：REMOTE SENSING （ 影响因子：4.1； 五年影响因子：4.8 ）

ISSN：

年卷期： 2025 年 17 卷 3 期

页码：

收录情况： SCI

摘要： Point cloud data, known for their accuracy and ease of acquisition, are commonly used for reconstructing level of detail 2 (LoD-2) building models. However, factors like object occlusion can cause incompleteness, negatively impacting the reconstruction process. To address this challenge, this paper proposes a method for reconstructing LoD-2 building models from incomplete point clouds. We design a generative adversarial network model that incorporates geometric constraints. The generator utilizes a multilayer perceptron with a curvature attention mechanism to extract multi-resolution features from the input data and then generates the missing portions of the point cloud through fully connected layers. The discriminator iteratively refines the generator's predictions using a loss function that is combined with plane-aware Chamfer distance. For model reconstruction, the proposed method extracts a set of candidate polygons from the point cloud and computes weights for each candidate polygon based on a weighted energy term tailored to building characteristics. The most suitable planes are retained to construct the LoD-2 building model. The performance of this method is validated through extensive comparisons with existing state-of-the-art methods, showing a 10.9% reduction in the fitting error of the reconstructed models, and real-world data are tested to evaluate the effectiveness of the method.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台