论文标题
自动驾驶中3D语义细分的域概括
Domain generalization of 3D semantic segmentation in autonomous driving
论文作者
论文摘要
使用深度学习，3D自动驾驶语义细分已成为一个经过充分研究的主题，其方法可以达到非常高的性能。尽管如此，由于培训数据集的大小有限，这些模型无法看到现实世界应用程序中发现的每种类型的对象和场景。在这些未知环境中可靠的能力称为\ textup {域概括}。 尽管它很重要，但在3D自动驾驶语义分段的情况下，域的概括相对尚未探索。为了填补这一空白，本文通过测试最先进的方法并讨论了解决激光成像检测和范围（LIDAR）域移动的难度。 我们还提出了第一种旨在解决此域概括的方法，我们称之为3DlabelProp。该方法依赖于利用LiDAR数据的几何形状和顺序性来通过在部分积累的点云上工作来增强其泛化性能。它的平均相交的平均相交（MIOU）的semanticposs为50.4％，而Pandaset固态激光雷达（Pandaset Solid-State LiDar）的平均相交是55.2％，而仅在Semantickitti接受训练时，它是概括的最先进方法（分别 +5％和 +33％的方法，分别是第二最佳方法）。 该方法的代码可在github上获得：https：//github.com/julessanchez/3dlabelprop。
Using deep learning, 3D autonomous driving semantic segmentation has become a well-studied subject, with methods that can reach very high performance. Nonetheless, because of the limited size of the training datasets, these models cannot see every type of object and scene found in real-world applications. The ability to be reliable in these various unknown environments is called \textup{domain generalization}. Despite its importance, domain generalization is relatively unexplored in the case of 3D autonomous driving semantic segmentation. To fill this gap, this paper presents the first benchmark for this application by testing state-of-the-art methods and discussing the difficulty of tackling Laser Imaging Detection and Ranging (LiDAR) domain shifts. We also propose the first method designed to address this domain generalization, which we call 3DLabelProp. This method relies on leveraging the geometry and sequentiality of the LiDAR data to enhance its generalization performances by working on partially accumulated point clouds. It reaches a mean Intersection over Union (mIoU) of 50.4% on SemanticPOSS and of 55.2% on PandaSet solid-state LiDAR while being trained only on SemanticKITTI, making it the state-of-the-art method for generalization (+5% and +33% better, respectively, than the second best method). The code for this method is available on GitHub: https://github.com/JulesSanchez/3DLabelProp.
