3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This can significantly hinder the navigation capabilities of self-driving vehicles. This paper advances the state of the art in this research field. Our first contribution consists in analysing a new unexplored scenario in point cloud segmentation, namely Source-Free Online Unsupervised Domain Adaptation (SF-OUDA). We experimentally show that state-of-the-art methods have a rather limited ability to adapt pre-trained deep network models to unseen domains in an online manner. Our second contribution is an approach that relies on adaptive self-training and geometric-feature propagation to adapt a pre-trained source model online without requiring either source data or target labels. Our third contribution is to study SF-OUDA in a challenging setup where source data is synthetic and target data is point clouds captured in the real world. We use the recent SynLiDAR dataset as a synthetic source and introduce two new synthetic (source) datasets, which can stimulate future synthetic-to-real autonomous driving research. Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds. Code and synthetic datasets are available at https://github.com/saltoricristiano/gipso-sfouda.
翻译:3D点云的语义分解是自主驱动的基础。 文献中的大多数方法都忽略了一个重要方面, 即如何在处理动态场景时处理域变换。 这会大大妨碍自驾驶飞行器的导航能力。 本文提高了研究领域的先进水平。 我们的第一种贡献是分析在点云分解中未探索的新的情景, 即源- 免费在线不受监督的Domain Aditective( SF- Free Oun- Oudvision Domain Addiction ) 。 我们实验性地显示, 最先进的方法在以在线方式将预先训练过的深深层网络模型调整到隐蔽域的能力相当有限。 我们的第二个贡献是一种依靠适应性自我培训和地理测量能力传播的方法, 以适应经过预先训练的源模型, 而不要求源数据或目标标签。 我们的第三种贡献是在一个挑战性的设置中研究SF- OUDA, 源数据是合成的点, 我们使用最近的 SynLiAR 数据集作为合成来源, 并引入两个新的合成(源) 数据集,, 可以促进我们现有的合成/ ASlobal- realbal- dislational developmental developmental- dreal- drodustrationaldrodustrual