Next Article in Journal
Assessing Spatial Correlations Between Land Cover Types and Land Surface Temperature Trends Using Vegetation Index Techniques in Google Earth Engine: A Case Study of Thessaloniki, Greece
Next Article in Special Issue
Closed and Structural Optimization for 3D Line Segment Extraction in Building Point Clouds
Previous Article in Journal
A Frequency Attention-Enhanced Network for Semantic Segmentation of High-Resolution Remote Sensing Images
Previous Article in Special Issue
FIFA3D: Flow-Guided Feature Aggregation for Temporal Three-Dimensional Object Detection
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Remote Sensing
Volume 17
Issue 3
10.3390/rs17030399
remotesensing-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

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

by
Ziqi Ding
1,
Yuefeng Lu
1,2,3,*,
Shiwei Shao
4,5,
Yong Qin
1,
Miao Lu
3,6,
Zhenqi Song
1 and
Dengkuo Sun
1
1
School of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255049, China
2
State Key Laboratory of Resources and Environmental Information System, Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
3
National Center of Technology Innovation for Comprehensive Utilization of Saline-Alkali Land, Dongying 257347, China
4
Wuhan Vocational College of Software and Engineering, Wuhan Open University, Wuhan 430205, China
5
Hubei Engineering Research Center for Intelligent Detection and Identification of Complex Parts, Wuhan 430205, China
6
State Key Laboratory of Efficient Utilization of Arid and Semi-Arid Arable Land in Northern China, The Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2025, 17(3), 399; https://doi.org/10.3390/rs17030399
Submission received: 18 December 2024 / Revised: 20 January 2025 / Accepted: 22 January 2025 / Published: 24 January 2025
(This article belongs to the Special Issue Advances in 3D Reconstruction Based on Remote Sensing Imagery and Lidar Point Cloud)
Browse Figures
Versions Notes

Abstract

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.
Keywords: three-dimensional reconstruction; point cloud processing; deep learning; point cloud completion three-dimensional reconstruction; point cloud processing; deep learning; point cloud completion

Share and Cite

MDPI and ACS Style

Ding, Z.; Lu, Y.; Shao, S.; Qin, Y.; Lu, M.; Song, Z.; Sun, D. Research on 3D Reconstruction Methods for Incomplete Building Point Clouds Using Deep Learning and Geometric Primitives. Remote Sens. 2025, 17, 399. https://doi.org/10.3390/rs17030399

AMA Style

Ding Z, Lu Y, Shao S, Qin Y, Lu M, Song Z, Sun D. Research on 3D Reconstruction Methods for Incomplete Building Point Clouds Using Deep Learning and Geometric Primitives. Remote Sensing. 2025; 17(3):399. https://doi.org/10.3390/rs17030399

Chicago/Turabian Style

Ding, Ziqi, Yuefeng Lu, Shiwei Shao, Yong Qin, Miao Lu, Zhenqi Song, and Dengkuo Sun. 2025. "Research on 3D Reconstruction Methods for Incomplete Building Point Clouds Using Deep Learning and Geometric Primitives" Remote Sensing 17, no. 3: 399. https://doi.org/10.3390/rs17030399

APA Style

Ding, Z., Lu, Y., Shao, S., Qin, Y., Lu, M., Song, Z., & Sun, D. (2025). Research on 3D Reconstruction Methods for Incomplete Building Point Clouds Using Deep Learning and Geometric Primitives. Remote Sensing, 17(3), 399. https://doi.org/10.3390/rs17030399

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop