From Coarse to Fine: Deep Prototype Refinement Network for Few-Shot Point Cloud Semantic Segmentation

Abstract

Few-shot point cloud semantic segmentation (FS-PCSS) aims to achieve precise segmentation of novel categories using only limited labeled samples. Existing prototype-based methods typically rely on shallow feature fusion strategies, failing to adequately model the feature distribution shift between support and query sets, resulting in insufficient prototype adaptation. To address this, we propose the Deep Prototype Refinement Network (DPR-Net), which systematically achieves progressive adaptation by constructing a coarse-to-fine prototype evolution trajectory. Our core Dynamic Prototype Refinement (DPR) module explicitly decomposes features into common and distinctive subspaces based on channel activation, enabling targeted adjustment of domain-sensitive features while preserving class-shared semantics. By cascading multiple refinement modules, we construct a prototype trajectory transitioning from support-biased to query-adapted representations, mitigating both under- and over-adaptation. Furthermore, our Mixture of Prototype Experts (MoPE) mechanism treats prototypes at different stages as complementary experts and adaptively ensembles their predictions through confidence-driven weighting. Extensive experiments demonstrate that DPR-Net achieves state-of-the-art performance with high efficiency. Notably, with only 0.28M parameters, DPR-Net achieves 80.76% mIoU on S3DIS (2-way 1-shot), representing a 15.92% improvement over the baseline.