Multi-Space Alignments Towards Universal LiDAR Segmentation

arXiv:2405.01538v1 Announce Type: cross
Abstract: A unified and versatile LiDAR segmentation model with strong robustness and generalizability is desirable for safe autonomous driving perception. This work presents M3Net, a one-of-a-kind framework for fulfilling multi-task, multi-dataset, multi-modality LiDAR segmentation in a universal manner using just a single set of parameters. To better exploit data volume and diversity, we first combine large-scale driving datasets acquired by different types of sensors from diverse scenes and then conduct alignments in three spaces, namely data, …

abstract arxiv autonomous autonomous driving cs.cv cs.lg cs.ro data dataset driving exploit framework kind lidar parameters perception robustness safe segmentation set space type universal work