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

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.