We present sDBSCAN, a scalable density-based clustering algorithm in high
dimensions with cosine distance. Utilizing the neighborhood-preserving property
of random projections, sDBSCAN can quickly identify core points and their
neighborhoods, the primary hurdle of density-based clustering. Theoretically,
sDBSCAN outputs a clustering structure similar to DBSCAN under mild conditions
with high probability. To further facilitate sDBSCAN, we present sOPTICS, a
scalable OPTICS for interactive exploration of the intrinsic clustering
structure. We also extend sDBSCAN and sOPTICS to L2, L1, $\chi^2$, and
Jensen-Shannon distances via random kernel features. Empirically, sDBSCAN is
significantly faster and provides higher accuracy than many other clustering
algorithms on real-world million-point data sets. On these data sets, sDBSCAN
and sOPTICS run in a few minutes, while the scikit-learn's counterparts demand
several hours or cannot run due to memory constraints.

我们提出了一个高效的基于密度的聚类算法 sDBSCAN，利用随机投影的邻域保持特性，能够快速识别核心点及其邻域，理论上，在合理条件下，sDBSCAN 的聚类结构与 DBSCAN 类似，具有较高的概率。sDBSCAN 在真实世界的百万点数据集上比其他聚类算法更快且提供更高的准确性。

基于随机投影的可扩展密度聚类

Scalable Density-based Clustering with Random Projections

Point cloud source data for surface reconstruction is usually contaminated
with noise and outliers. To overcome this deficiency, a density-based point
cloud denoising method is presented to remove outliers and noisy points. First,
particle-swam optimization technique is employed for automatically
approximating optimal bandwidth of multivariate kernel density estimation to
ensure the robust performance of density estimation. Then, mean-shift based
clustering technique is used to remove outliers through a thresholding scheme.
After removing outliers from the point cloud, bilateral mesh filtering is
applied to smooth the remaining points. The experimental results show that this
approach, comparably, is robust and efficient.

该论文提出了一种基于密度的点云去噪方法，该方法使用粒子群优化技术来自动逼近多变量核密度估计的最优带宽，并使用均值漂移聚类技术通过阈值方案来除去离群点。去除离群点后，应用双边网格滤波来平滑剩余点。实验结果表明，该方法是鲁棒和有效的。