filters.eigenvalues returns the eigenvalues for a given point, based on its k-nearest neighbors.

The filter produces three new dimensions (Eigenvalue0, Eigenvalue1, and Eigenvalue2), which can be analyzed directly, or consumed by downstream stages for more advanced filtering. The eigenvalues are sorted in ascending order.

The eigenvalue decomposition is performed using Eigen’s SelfAdjointEigenSolver. For more information see

Default Embedded Stage

This stage is enabled by default


This pipeline demonstrates the calculation of the eigenvalues. The newly created dimensions are written out to BPF for further inspection.



The number of k-nearest neighbors. [Default: 8]