Deconvolution with partially known kernel of nonnegative signals

@article{Barone1990DeconvolutionWP,
  title={Deconvolution with partially known kernel of nonnegative signals},
  author={F. Barone and C. Rossi},
  journal={Machine Vision and Applications},
  year={1990},
  volume={3},
  pages={107-115}
}
This paper extends the Bayesian direct deconvolution method to the case in which the convolution kernel depends on few unknown nuisance parameters. Moreover, an acceleration procedure is proposed that drastically reduces the computational burden. Finally, the implementation of the method by means of the fast Fourier transform is fully discussed in the multidimensional case.