App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 11

Gsf-net: indoor point cloud segmentation network fusing dual-stream geometric interaction and edge-aware sampling

Li Sha1
Wang Zhongyuan1
1. School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China
DOI: 10.19734/j.issn.1001-3695.2026.02.0079

Abstract

Indoor point cloud semantic segmentation suffers from ambiguous local geometric structure perception and the loss of high-frequency details during downsampling. This paper proposes GSF-Net, an indoor point cloud segmentation network that integrates dual-stream geometric interaction and edge-aware sampling. The network designs a dual-stream geometric-semantic fusion module. The module contains a semantic-aware stream and a rigid geometric probing stream, which interact in parallel to improve the discrimination of objects with similar geometric structures but different semantic categories, such as walls and blackboards. The network further introduces an Edge Sampling (SAES) strategy. SAES uses information entropy to quantify the uncertainty of local feature distributions. SAES builds a hybrid sampling mechanism that prioritizes edge skeletons and uses farthest point sampling to maintain global coverage. GSF-Net achieves 61.5% mIoU on the S3DIS Area 5 benchmark and improves performance in several representative categories, while maintaining low model complexity with 5.4M parameters and 8.6G FLOPs. The results demonstrate that GSF-Net effectively improves boundary preservation and semantic discrimination in indoor point cloud segmentation under low computational cost.

Foundation Support

国家自然科学基金项目(42274048)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.02.0079
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 11

Publish History

[2026-07-09] Accepted Paper

Cite This Article

李莎, 王中元. GSF-Net：融合双流几何交互与边缘感知采样的室内点云分割网络 [J]. 计算机应用研究, 2026, 43 (11). (2026-07-31). https://doi.org/10.19734/j.issn.1001-3695.2026.02.0079. (Li Sha, Wang Zhongyuan. Gsf-net: indoor point cloud segmentation network fusing dual-stream geometric interaction and edge-aware sampling [J]. Application Research of Computers, 2026, 43 (11). (2026-07-31). https://doi.org/10.19734/j.issn.1001-3695.2026.02.0079. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)