Building Point Cloud Segmentation via 2D–3D Fusion Based on Colmap

  • Lu Chuanchuan*
  • , Gong Guanghong
  • , Li Ying
  • , Li Ni
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

3D point cloud segmentation is a key task in urban scene reconstruction, especially for extracting building structures, which are diverse in scale and geometry. Existing segmentation methods mainly rely on supervised deep learning, which suffers from limited generalization across different scenes and requires large amounts of annotated 3D data and computational resources. In contrast, 2D image segmentation has achieved significant progress. This work proposes a generalized 3D building segmentation framework based on 2D–3D fusion. By leveraging state-of-the-art 2D segmentation models such as Mask2Former and SAM, and combining them with 3D point clouds reconstructed by COLMAP, we establish correspondences between 2D masks and 3D points. This approach enables effective segmentation of 3D buildings without 3D supervision, and lays a foundation for downstream tasks such as urban scene reconstruction, measurement, and mapping.

Original languageEnglish
Title of host publicationIntelligent Simulation - 37th China Simulation Conference, CSC 2025, Proceedings
EditorsYin Liu, Ni Li, Xiao Song, Yinan Guo
PublisherSpringer Science and Business Media Deutschland GmbH
Pages282-295
Number of pages14
ISBN (Print)9789819527502
DOIs
StatePublished - 2026
Event37th China Simulation Conference, CSC 2025 - Hefei, China
Duration: 31 Oct 20252 Nov 2025

Publication series

NameCommunications in Computer and Information Science
Volume2679 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference37th China Simulation Conference, CSC 2025
Country/TerritoryChina
CityHefei
Period31/10/252/11/25

Keywords

  • 2D-3D fusion
  • building point cloud
  • multi-view fusion
  • point cloud segmentation

Fingerprint

Dive into the research topics of 'Building Point Cloud Segmentation via 2D–3D Fusion Based on Colmap'. Together they form a unique fingerprint.

Cite this