High-quality point cloud annotation is labor-intensive and time-consuming, but it serves as a critical factor driving the success of LiDAR point cloud semantic segmentation. Leveraging low-quality labels in LiDAR point cloud processing is overlooked, despite the fact that noisy annotation has low labeling costs and abundant cross-modal resources (e.g., labels from images). To this end, we thoroughly investigate the performance of airborne LiDAR point cloud semantic segmentation models using noisy labels for the first time and find that it is closely related to object categories and learning stages. Then we propose a new semantic segmentation framework for LiDAR point cloud noisy learning called adaptive dynamic noise label correction (ADNLC), which consists of weak category priority, dynamic monitoring (DM), and historical choice (HC). With these methods, we can adaptively correct the noise labels of different categories according to their specific learning situations. Finally, we provide a comprehensive process for noise simulation, accuracy evaluation, and comparisons in airborne LiDAR point cloud learning from noisy labels. We conduct experiments on the ISPRS 3-D Labeling Vaihingen and Large-scale ALS data for Semantic Labeling in Dense Urban Areas (LASDU) datasets, and the results show that our ADNLC outperforms baseline methods by 30% and 16%, respectively, verifying the superiority of ADNLC and demonstrating the potential of noise labels in LiDAR data processing.

中文翻译：

---

带有噪声标签的机载 LiDAR 点云的语义分割


高质量的点云标注既费力又耗时，但却是推动激光雷达点云语义分割成功的关键因素。尽管噪声注释具有较低的标记成本和丰富的跨模态资源（例如，来自图像的标签），但在激光雷达点云处理中利用低质量标签却被忽视了。为此，我们首次深入研究了使用噪声标签的机载激光雷达点云语义分割模型的性能，发现它与物体类别和学习阶段密切相关。然后，我们提出了一种用于激光雷达点云噪声学习的新语义分割框架，称为自适应动态噪声标签校正（ADNLC），它由弱类别优先级、动态监控（DM）和历史选择（HC）组成。通过这些方法，我们可以根据不同类别的具体学习情况自适应地纠正不同类别的噪声标签。最后，我们提供了一个全面的流程，用于机载激光雷达点云从噪声标签学习中的噪声模拟、精度评估和比较。我们对 ISPRS 3-D Labeling Vaihingen 和 Large-scale ALS data for Semantic Labeling in Dense Urban Areas (LASDU) 数据集进行了实验，结果表明我们的 ADNLC 分别优于基线方法 30% 和 16%，验证了ADNLC 的优越性并展示了噪声标签在激光雷达数据处理中的潜力。