用采样+最近邻法加速点云实例分割，大幅降低内存占用。
Instance Segmentation for Point Sets
- 对点云进行采样后分割，再用最近邻扩展标签
- 随机采样策略在大样本下性能稳定，速度提升显著
- 适合大规模点云实时分割场景
PointNet [QSMG16] 和 PointNet++ [QYSG17] 等神经网络架构使深度学习可用于3D点集。这些网络学习的形状特征表示已成功用于语义分割，并通过相似性分组提案网络（SGPN）[WYHN17] 实现了实例分割。然而，SGPN 的作者指出其使用内存密集的相似性矩阵，内存开销随点数呈二次增长。本文提出两种基于采样的方法：在子采样点集上进行实例分割，再通过最近邻方式将标签外推至完整点集。两种方法在大子样本下表现相当，但随机采样策略在速度和内存使用上优化最明显。
原文摘要 · Abstract (English)
Recently proposed neural network architectures like PointNet [QSMG16] and PointNet++ [QYSG17] have made it possible to apply Deep Learning to 3D point sets. The feature representations of shapes learned by these two networks enabled training classifiers for Semantic Segmentation, and more recently for Instance Segmentation via the Similarity Group Proposal Network (SGPN) [WYHN17]. One area of improvement which has been highlighted by SGPN's authors, pertains to use of memory intensive similarity matrices which occupy memory quadratic in the number of points. In this report, we attempt to tackle this issue through use of two sampling based methods, which compute Instance Segmentation on a sub-sampled Point Set, and then extrapolate labels to the complete set using the nearest neigbhour approach. While both approaches perform equally well on large sub-samples, the random-based strategy gives the most improvements in terms of speed and memory usage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。