Existing fully-supervised point cloud segmentation methods suffer in the dynamic testing environment with emerging new classes. Few-shot point cloud segmentation algorithms address this problem by learning to adapt to new classes at the sacrifice of segmentation accuracy for the base classes, which severely impedes its practicality. This largely motivates us to present the first attempt at a more practical paradigm of generalized few-shot point cloud segmentation, which requires the model to generalize to new categories with only a few support point clouds and simultaneously retain the capability to segment base classes. We propose the geometric words to represent geometric components shared between the base and novel classes, and incorporate them into a novel geometric-aware semantic representation to facilitate better generalization to the new classes without forgetting the old ones. Moreover, we introduce geometric prototypes to guide the segmentation with geometric prior knowledge. Extensive experiments on S3DIS and ScanNet consistently illustrate the superior performance of our method over baseline methods. Our code is available at: https://github.com/Pixie8888/GFS-3DSeg_GWs.

翻译：现有全监督点云分割方法在动态测试环境中面对新出现的类别时表现不佳。少样本点云分割算法通过学习适应新类别解决了这一问题，但牺牲了基类别的分割精度，严重阻碍了其实用性。这促使我们首次提出更具实用性的广义少样本点云分割范式，要求模型仅通过少量支持点云即可泛化至新类别，同时保持分割基类别的能力。我们提出用"几何词汇"表示基类与新类之间共享的几何组件，并将其融入新型几何感知语义表征中，以在遗忘旧类别的同时促进对新类别的泛化。此外，我们引入几何原型利用几何先验知识指导分割。在S3DIS和ScanNet数据集上的大量实验表明，我们的方法性能始终优于基线方法。代码开源地址：https://github.com/Pixie8888/GFS-3DSeg_GWs