This work proposes to evaluate the effects of a spatially adaptive filter called NDSAR-BLF (N-Dimensional SAR Bilateral Filter) on scatterer separation and height estimation from SAR tomograms. We have developed a spatial simulation procedure allowing to generate a tomographic image stack from a simple 3D building model, assuming a multi-track airborne configuration and a distributed target model incorporating multi-dimensional speckle. Inversion of such a model requires the estimation of a covariance matrix from the data. We show the importance of spatial adaptivity in covariance estimation by comparing the 3D reconstructions obtained with our filter and the boxcar filter. Our experiments show the ability of the NDSAR-BLF to improve height estimation and scatterer separation in layover areas thanks to its smoothing and edge preserving properties.