arXiv · 1110.2227
Average Interpolating Wavelets on Point Clouds and Graphs
Abstract
We introduce a new wavelet transform suitable for analyzing functions on point clouds and graphs. Our construction is based on a generalization of the average interpolating refinement scheme of Donoho. The most important ingredient of the original scheme that needs to be altered is the choice of the interpolant. Here, we define the interpolant as the minimizer of a smoothness functional, namely a generalization of the Laplacian energy, subject to the averaging constraints. In the continuous setting, we derive a formula for the optimal solution in terms of the poly-harmonic Green's function. The form of this solution is used to motivate our construction in the setting of graphs and point clouds. We highlight the empirical convergence of our refinement scheme and the potential applications of the resulting wavelet transform through experiments on a number of data stets.
Explore related subjects
Keep this discovery
Raif M. Rustamov. 2011-10-10. Average Interpolating Wavelets on Point Clouds and Graphs. https://arxiv.org/abs/1110.2227
Cite the original work for its findings. Save a collection to share your selection of sources.