EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GENet: A Geometry-Enhanced Network for LiDAR Semantic Segmentation

Yuchen Wu, Hanbing Wei

Sensors · 26.02.2026 · 26 (5) · 1460

DOI: 10.3390/s26051460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.02.2026. Verfasst von Yuchen Wu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

LiDAR has been widely applied in autonomous driving and mobile robotics. Recently, many studies focus on real-time point cloud segmentation, aiming to achieve higher accuracy while maintaining real-time inference speed. Current real-time methods mostly rely on 2D projection, which inevitably leads to spatial information loss. To address the limitations of 2D projection methods, we propose a Geometry-Enhanced Network called GENet that exploits spatial priors. The network employs an Atrous Separable Range Attention (ASRA) module to explicitly utilize spatial priors from range images, enabling geometry-aware feature aggregation with large receptive field at linear complexity. A Geometry-Context Modulation (GCM) mechanism is then used to calibrate semantic features, incorporating geometric priors while preserving the discriminative ability of original features across different categories. Experiments show that our method achieves efficient information fusion while maintaining real-time performance. Compared to existing methods, GENet requires fewer parameters and less computation, achieving a favorable balance between accuracy and efficiency.

Schlagwörter

Stichwörter der Autor:innen

LiDAR point cloudfeature fusiongeometry attentionrange viewsemantic segmentation

Autor:innen und Institutionen

  • School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wu, Y., & Wei, H. (2026). GENet: A Geometry-Enhanced Network for LiDAR Semantic Segmentation. Sensors, 26(5), 1460. https://doi.org/10.3390/s26051460

Vancouver

Wu Y, Wei H. GENet: A Geometry-Enhanced Network for LiDAR Semantic Segmentation. Sensors. 2026;26(5):1460. doi:10.3390/s26051460

BibTeX
@article{Wu2026,
  author = {Wu, Yuchen and Wei, Hanbing},
  title = {GENet: A Geometry-Enhanced Network for LiDAR Semantic Segmentation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {5},
  pages = {1460},
  doi = {10.3390/s26051460}
}
Kostenlos starten →