Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation

ArXi:2603.19757v1 Announce Type: cross Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated examples. Existing prototype-based methods typically construct compact and deterministic prototypes from the set to guide query segmentation. However, such rigid representations are unable to capture the intrinsic uncertainty