EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GACM-Net: A Geometry-Aware Contextual Memory Network for Efficient 3D Point Cloud Understanding

Dongzhen Liu, Yuzhong Deng, Haojie Wu, Jian He, Jianxiao Zou, Shicai Fan

Electronics · 12.08.2026 · 15 (16) · 3577

DOI: 10.3390/electronics15163577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 12.08.2026. Verfasst von Dongzhen Liu und 5 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Three-dimensional point cloud understanding plays an important role in autonomous perception, robotic navigation, and LiDAR-based remote sensing. However, the irregular and unordered nature of point clouds makes it challenging to model long-range contextual dependencies while preserving geometric awareness, particularly under noise, occlusion, and non-uniform sampling. To address these challenges, we propose a Geometry-Aware Contextual Memory Network (GACM-Net) for 3D point cloud analysis. Specifically, an Adaptive Geometric Prior Encoding (AdGPE) module is introduced to dynamically coordinate multiple geometric priors, including absolute coordinates, center-relative coordinates, and distance-based cues, thereby enhancing geometry-aware contextual interaction during long-range propagation. Furthermore, a Structure-Aware Point Memory Unit (SAPM) is designed to achieve stable contextual memory learning through normalized gate interaction, peephole memory regulation, gated candidate filtering, and residual feature propagation. Based on SAPM, a Bidirectional Structure-Aware Point Memory module (BiSAPM) further captures complementary geometric dependencies from opposite propagation directions, improving contextual completeness and structural consistency for irregular point cloud representations. Extensive experiments on ModelNet40, ScanObjectNN, and ShapeNetPart demonstrate that GACM-Net achieves competitive classification and part segmentation performance with a compact model size and favorable computational efficiency. The results further show that the proposed framework provides a good balance among accuracy, efficiency, and robustness for 3D point cloud understanding.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program

Zitieren

APA

Liu, D., Deng, Y., Wu, H., He, J., Zou, J., & Fan, S. (2026). GACM-Net: A Geometry-Aware Contextual Memory Network for Efficient 3D Point Cloud Understanding. Electronics, 15(16), 3577. https://doi.org/10.3390/electronics15163577

Vancouver

Liu D, Deng Y, Wu H, He J, Zou J, Fan S. GACM-Net: A Geometry-Aware Contextual Memory Network for Efficient 3D Point Cloud Understanding. Electronics. 2026;15(16):3577. doi:10.3390/electronics15163577

BibTeX
@article{Liu2026,
  author = {Liu, Dongzhen and Deng, Yuzhong and Wu, Haojie and He, Jian and Zou, Jianxiao and Fan, Shicai},
  title = {GACM-Net: A Geometry-Aware Contextual Memory Network for Efficient 3D Point Cloud Understanding},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {16},
  pages = {3577},
  doi = {10.3390/electronics15163577}
}
Kostenlos starten →