MSSP：面向3D点云无监督语义分割的多尺度空间约束划分
MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation of 3D Point Clouds
- College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学学院）
- School of Electronics and Communication Engineering, Sun Yat-sen University（中山大学电子与通信工程学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对无监督3D点云语义分割，提出MSSP框架，结合多尺度谱分析与空间约束聚类，在S3DIS和ScanNet上取得最优mIoU，并揭示空间一致性是多尺度表示有效的前提。
AI中文摘要：
3D点云语义分割对于现实世界的空间理解至关重要，然而人工标注的高昂成本促使了无需标签的无监督方法的发展。现有的基于超点的方法通常依赖于固定粒度下的谱分析，无法捕捉复杂室内场景中固有的层次化语义结构。为弥补这一差距，我们提出了一种多尺度空间约束划分（MSSP）框架，该框架将多尺度谱分析与空间约束聚类相结合。多尺度谱分析在多个聚类粒度上构建丰富的超点描述符；然而，由此产生的高维特征空间需要结构先验才能转化为更清晰的分割。空间约束聚类通过将超点合并限制在物理相邻区域来提供这种先验，从而施加多尺度特征有效所需的空间一致性。在S3DIS和ScanNet上的大量实验表明，MSSP在主要基准上取得了无监督方法中最佳的mIoU，在S3DIS上尤其显著。值得注意的是，我们的消融研究揭示了一种“先正则化后丰富”的交互作用：仅有多尺度特征并不能改善最终分割，但当与空间正则化结合时却变得高度有效，这强调了空间一致性是超点聚类中多尺度表示的先决条件。
英文摘要：
3D point cloud semantic segmentation is essential for real-world spatial understanding, yet the prohibitive cost of human annotations motivates unsupervised approaches that require no labels. Existing superpoint-based methods typically rely on spectral analysis at a fixed granularity, failing to capture the hierarchical semantic structures inherent in complex indoor scenes. To bridge this gap, we present a Multi-Scale Spatially-Constrained Partition (MSSP) framework that combines multi-scale spectral analysis with spatially-constrained clustering. Multi-scale spectral analysis constructs enriched superpoint descriptors across multiple clustering granularities; however, the resulting high-dimensional feature space calls for a structural prior to translate into cleaner segmentation. Spatially-constrained clustering supplies this prior by restricting superpoint merging to physically adjacent regions, imposing the spatial coherence needed for multi-scale features to be effective. Extensive experiments on S3DIS and ScanNet show that MSSP achieves the best mIoU among unsupervised methods on the main benchmarks, with particularly significant gains on S3DIS. Notably, our ablation reveals a regularize-then-enrich interaction: multi-scale features alone do not improve final segmentation, yet become highly effective when coupled with spatial regularization, underscoring that spatial coherence is aprerequisite for multi-scale representations in superpoint clustering.
