面向点云分割新类发现的几何感知超图推理
Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation
将超图结构引入点云分割的新类发现任务，用高阶关联替代二值关联进行类间推理，并设计几何感知原型增强空间信息，可复用于开放世界点云分割或跨类知识迁移。
原文依据 we introduce a hypergraph structure to model high-order associations among classes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论点云分割中的新类发现是近期提出的任务，旨在利用已知类别的知识来自动分割点云中未标注的类别。该任务的核心在于利用多个已知类别的几何与语义知识来实现对新类别的语义理解与分割。然而，现有方法忽略了已知类与新类之间的高阶关联，仅依赖二值关联进行类别分配和新类推理，导致语义分割不够精确。为解决这些问题，我们引入超图结构来建模类别间的高阶关联，实现从已知类到新类的协同推理，超越了传统的二值关系。此外，现有方法在处理点云数据时过度关注语义信息的提取，忽视了几何特征的重要性。为此，我们引入几何感知原型，增强模型捕获几何空间信息的能力。通过超边传播几何信息，我们的方法增强了对类别间空间分布的理解，提高了分割精度。在SemanticKITTI和SemanticPOSS数据集上取得的显著性能提升证明了我们方法的优越性。
英文原文摘要 1412 字符
Novel Class Discovery in Point Cloud Segmentation is recently proposed, aiming to leverage knowledge from known classes to automatically segment unlabeled classes within point clouds. The core of this task lies in leveraging the geometric and semantic knowledge of multiple known classes to achieve semantic understanding and segmentation of novel classes.However, existing methods overlook the high-order associations between known and novel classes, relying solely on binary associations for class assignment and novel class reasoning, which leads to less precise semantic segmentation.To address these issues, we introduce a hypergraph structure to model high-order associations among classes, enabling collaborative reasoning from known classes to novel classes, extending beyond traditional binary relations.Additionally, existing methods focus excessively on extracting semantic information when processing point cloud data, neglecting the importance of geometric features. To address this, we introduce Geometric-Aware Prototypes, enhancing the model's ability to capture geometric spatial information.By propagating geometric information through hyperedges, our method enhances the understanding of spatial distributions across classes, improving segmentation accuracy.Significant performance improvements achieved on the SemanticKITTI and SemanticPOSS datasets demonstrate the superiority of our method.