Multivariant Kernel Regression and Smoothing

A multivariant Gaussian kernel regression and smoothing tool.

This function implements multivariant Gaussian kernel regression and smoothing. A few examples show how it can be used to smooth 3-d noisy images with missing data.

For tutorial purpose, the function is implemented in the simplest form. Therefore, it is particularly suitable for beginners to learn kernel regression.

The efficiency is improved in the updated version by searching neighbours in the effective range.