3D-UMamba: 3D U-Net with state space model for semantic segmentation of multi-source LiDAR point clouds

Published: 01 Jan 2025, Last Modified: 16 May 2025Int. J. Appl. Earth Obs. Geoinformation 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Proposing a new Mamba-based LiDAR point cloud segmentation framework, 3D-UMamba.•Designing a novel Voxel-based Token Serialization method with a Bi-Scanning strategy.•Experiments demonstrated the SOTA performance of Mamba in multi-source LiDAR data.
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview