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, feature, and label spaces, during the training. As a result, M3Net is capable of taming heterogeneous data for training state-of-the-art LiDAR segmentation models. Extensive experiments on twelve LiDAR segmentation datasets verify our effectiveness. Notably, using a shared set of parameters, M3Net achieves 75.1%, 83.1%, and 72.4% mIoU scores, respectively, on the official benchmarks of SemanticKITTI, nuScenes, and Waymo Open.

翻译：为实现安全的自动驾驶感知，一个统一且通用的激光雷达分割模型需要具备强鲁棒性和泛化能力。本文提出M3Net，这是一种独特框架，能以通用方式仅用单组参数实现多任务、多数据集、多模态的激光雷达分割。为了更好地利用数据量和多样性，我们首先整合来自不同场景、由不同类型传感器采集的大规模驾驶数据集，随后在训练过程中对数据空间、特征空间和标签空间三个维度进行对齐。通过这种方式，M3Net能够驯服异构数据，以训练最先进的激光雷达分割模型。在十二个激光雷达分割数据集上的大量实验验证了我们的有效性。值得注意的是，M3Net使用共享参数集，在SemanticKITTI、nuScenes和Waymo Open的官方基准测试上分别达到75.1%、83.1%和72.4%的mIoU分数。