Interpolation of Discretely-Sampled Density Fields

We present a new technique for the interpolation of discretely-sampled non-negat ive scalar fields across regions of missing data. Any set of basis functions can be used, though the method is fastest when they are close to orthogonal. We sho w how the technique may be efficiently applied when the discrete sampling rate v aries across the field. Regularisation is desirable to avoid over-fitting noisy data, and is necessary when the regions of missing data are larger than the requ ired resolution. We present and investigate methods for such regularisation.