Hierarchical local global transformer for point clouds analysis

Autor: Dilong Li, Shenghong Zheng, Ziyi Chen, Xiang Li, Lanying Wang, Jixiang Du
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: International Journal of Applied Earth Observations and Geoinformation, Vol 129, Iss , Pp 103813- (2024)
Druh dokumentu: article
ISSN: 1569-8432
DOI: 10.1016/j.jag.2024.103813
Popis: Transformer networks have demonstrated remarkable performance in point cloud analysis. However, achieving a balance between local regional context and global long-range context learning remains a significant challenge. In this paper, we propose a Hierarchical Local Global Transformer Network (LGTNet), designed to capture local and global contexts in a hierarchical manner. Specifically, we employ serial local and global Transformers to learn the inner-group and cross-group self-attention, respectively. Besides, we propose a geometric moment-based position encoding for local Transformer, enabling the embedding of comprehensive local geometric relationship. Additionally, we also introduce a global feature pooling module that extracts the global features from each encoder layers. Extensive experimental results demonstrate that LGTNet achieves state-of-the-art performance on ShapeNetPart and ScanObjectNN datasets. This approach effectively enhances the understanding of point cloud scenes, thereby facilitating the use of point cloud data in remote sensing applications.
Databáze: Directory of Open Access Journals