Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation

2026-06-05

AI Summary

This work addresses the limitations of existing methods in point cloud novel class discovery, which rely solely on pairwise associations and thus inadequately model inter-class relationships and underutilize geometric information. To overcome these issues, we introduce a hypergraph-based reasoning framework that leverages high-order associations—a first in this domain. Our approach employs hypergraph neural networks to capture complex collaborative relationships between known and novel classes and incorporates geometry-aware prototypes to enrich class-level geometric representations. Experimental results on SemanticKITTI and SemanticPOSS demonstrate that our method significantly outperforms current state-of-the-art techniques, achieving notably higher accuracy in novel class segmentation and validating the effectiveness of jointly reasoning over high-order semantics and spatial structure.

Abstract

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.

Problem

• novel class discovery
• point cloud segmentation
• hypergraph reasoning
• geometric information
• high-order associations

Innovation

• hypergraph reasoning
• novel class discovery
• point cloud segmentation
• geometric-aware prototypes
• high-order associations