LGMamba: Large-Scale ALS Point Cloud Semantic Segmentation With Local and Global State-Space Model

作     者：Li, Dilong Zhao, Jing Chang, Chongkei Chen, Ziyi Du, Jixiang 

作者机构：Huaqiao Univ Coll Comp Sci & Technol Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Key Lab Data Secur & Blockchain TechnolFuj Xiamen 361021 Peoples R China 

出 版 物：《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》 (IEEE Geosci. Remote Sens. Lett.)

年 卷 期：2025年第22卷

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0708[理学-地球物理学] 0816[工学-测绘科学与技术] 

基　　金：National Natural Science Foundation of China [42201475, 62001175] Natural Science Foundation of Fujian Province [2021J05059, 2023J01135] Fundamental Research Funds for the Central Universities of Huaqiao University [ZQN-1114] Natural Science Foundation of Fujian Province Fundamental Research Funds for the Central Universities of Huaqiao University 

主　　题：Point cloud compression Feature extraction Semantic segmentation Training Three-dimensional displays Convolution Transformers Encoding Indexes Semantics Airborne laser scanning (ALS) Mamba semantic segmentation state-space models (SSMs) 

摘      要：The large scale and extensive coverage of point cloud data make large-scale airborne laser scanning (ALS) point cloud semantic segmentation a highly challenging task. Although transformers have shown impressive performance in large-scale point cloud semantic segmentation task, their quadratic complexity limits the processing capacity. To alleviate this issue, we propose Local and Global Mamba (LGMamba)-a novel state-space model (SSM)-based network for large-scale point cloud semantic segmentation. Specifically, we propose Local Mamba module to extract fine-grained local features by effectively capturing local dependencies. Then, we propose Global Mamba module to refine the learned local features by capturing the global long-distance dependencies of whole scenes. The validation of our method on the DALES datasets was conducted. Extensive experimental results demonstrate the effectiveness of LGMamba, with mean intersection over union (mIoU) of 82.3% and overall accuracy (OA) of 97.7% on DALES.