Exploring Token Serialization for Mamba-Based LiDAR Point Cloud Segmentation

LiDAR point cloud segmentation has increasingly benefited from the application of Mamba-based models. However, the unordered and irregular natures of point clouds necessitate serialization, which significantly impacts the performance of Mamba-based methods. This article explores the critical role of token serialization in Mamba-based point cloud processing, using the pure Mamba network, PointMamba, as the baseline. We systematically investigated existing point cloud serialization methods, evaluating their performance on two challenging LiDAR datasets: the airborne MultiSpectral LiDAR (MS-LiDAR) dataset and the aerial Dayton annotated LiDAR Earth scan (DALES) dataset. To explore the inherent factors of serialization contributing to Mamba’s performance, we design novel indicators for serialization quality, focusing on spatial and semantic proximity. These indicators are validated across all datasets, offering a valuable reference and guidance for advancing token serialization in Mamba-based point cloud processing. Guided by these indicators, we proposed a new point cloud serialization method that integrates spatial and semantic features through a weighted comprehensive distance matrix. The proposed method achieves superior accuracy on both LiDAR datasets, surpassing existing approaches, and establishes a strong foundation for advancing Mamba-based point cloud processing.