Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation
This work addresses the problem of discovering novel classes in point cloud segmentation, a task critical for autonomous driving and robotics, by improving upon existing pairwise association methods.
The paper introduces a hypergraph-based framework for novel class discovery in point cloud segmentation, which models high-order associations among classes and uses geometric-aware prototypes to enhance spatial understanding. The method achieves state-of-the-art performance on SemanticKITTI and SemanticPOSS datasets.
Novel class discovery in point cloud segmentation aims to transfer knowledge from known classes to automatically identify and segment unlabeled novel classes in point clouds. Existing methods mainly rely on pairwise associations for class assignment and novel class reasoning, which limits their ability to capture complex relationships among known and novel classes and may lead to inaccurate semantic segmentation. To address this issue, we introduce a hypergraph-based framework that models high-order associations among classes and enables collaborative reasoning from known classes to novel classes beyond traditional pairwise relations. Moreover, existing methods tend to focus on semantic feature extraction while paying insufficient attention to geometric information in point clouds. To better exploit spatial structure, we propose Geometric-Aware Prototypes to enhance the representation of class-level geometric cues. By propagating geometric information through hyperedges, the proposed method improves the understanding of spatial distributions across classes and leads to more accurate segmentation. Experiments on the SemanticKITTI and SemanticPOSS datasets demonstrate the effectiveness and superiority of our method.