In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is to setup the exact correlations between the point representations and their base class labels, as well as the representation correlations between the points from base and novel classes. A coarse or statistical correlation learning may lead to the confusion in novel class inference. lf we impose a causal relationship as a strong correlated constraint upon the learning process, the essential point cloud representations that accurately correspond to the classes should be uncovered. To this end, we introduce a structural causal model (SCM) to re-formalize the 3D-NCD problem and propose a new method, i.e., Joint Learning of Causal Representation and Reasoning. Specifically, we first analyze hidden confounders in the base class representations and the causal relationships between the base and novel classes through SCM. We devise a causal representation prototype that eliminates confounders to capture the causal representations of base classes. A graph structure is then used to model the causal relationships between the base classes' causal representation prototypes and the novel class prototypes, enabling causal reasoning from base to novel classes. Extensive experiments and visualization results on 3D and 2D NCD semantic segmentation demonstrate the superiorities of our method.

翻译：本文聚焦于点云分割新类别发现（3D-NCD）任务，旨在利用已标注（基类）三维类别的监督信息，学习能够分割未标注（新类）三维类别的模型。该任务的关键在于建立点表示与其基类标签之间的精确关联，以及基类与新类点表示之间的关联关系。粗糙或统计层面的关联学习可能导致新类推断的混淆。若在学习过程中引入因果关系作为强关联约束，则能够揭示与类别精确对应的本质性点云表示。为此，我们引入结构因果模型（SCM）重新形式化3D-NCD问题，并提出一种新方法——因果表示与推理联合学习。具体而言，我们首先通过SCM分析基类表示中的隐藏混杂因子以及基类与新类间的因果关系。我们设计了能够消除混杂因子的因果表示原型，以捕获基类的因果表示。随后采用图结构建模基类因果表示原型与新类原型间的因果关系，实现从基类到新类的因果推理。在三维与二维NCD语义分割任务上的大量实验与可视化结果验证了本方法的优越性。