GeoSegNet : point cloud semantic segmentation via geometric encoder–decoder modeling

Chen CHEN, Yisen WANG, Honghua CHEN, Xuefeng YAN*, Dayong REN, Yanwen GUO, Haoran XIE, Fu Lee WANG, Mingqiang WEI

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)


Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding. Although significant advances in recent years, most of the existing methods still suffer from either the object-level misclassification or the boundary-level ambiguity. In this paper, we present a robust semantic segmentation network by deeply exploring the geometry of point clouds, dubbed GeoSegNet. Our GeoSegNet consists of a multi-geometry-based encoder and a boundary-guided decoder. In the encoder, we develop a new residual geometry module from multi-geometry perspectives to extract object-level features. In the decoder, we introduce a contrastive boundary learning module to enhance the geometric representation of boundary points. Benefiting from the geometric encoder–decoder modeling, GeoSegNet infers the segmentation of objects effectively while making the intersections (boundaries) of two or more objects clear. GeoSegNet achieves a significant performance with 64.9% mIoU on the challenging S3DIS dataset (Area 5) and 70.2% mIoU on S3DIS sixfold. Experiments show obvious improvements of GeoSegNet over its competitors in terms of the overall segmentation accuracy and object boundary clearness. Code is available at .

Original languageEnglish
JournalVisual Computer
Publication statusE-pub ahead of print - 29 May 2023

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.


  • Contrastive boundary learning
  • GeoSegNet
  • Point cloud semantic segmentation
  • Residual geometry module


Dive into the research topics of 'GeoSegNet : point cloud semantic segmentation via geometric encoder–decoder modeling'. Together they form a unique fingerprint.

Cite this