Spatially adaptive estimation via fitted local likelihood techniques

Vladimir Katkovnik, Vladimir Spokoiny

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)


This paper offers a new technique for spatially adaptive estimation. The local likelihood is exploited for nonparametric modeling of observations and estimated signals. The approach is based on the assumption of a local homogeneity of the signal: for every point there exists a neighborhood in which the signal can be well approximated by a constant. The fitted local likelihood statistics are used for selection of an adaptive size and shape of this neighborhood. The algorithm is developed for a quite general class of observations subject to the exponential distribution. The estimated signal can be uni- and multivariable. We demonstrate a good performance of the new algorithm for image denoising and compare the new method versus the intersection of confidence interval (ICI) technique that also exploits a selection of an adaptive neighborhood for estimation.

Original languageEnglish
Pages (from-to)873-886
Number of pages14
JournalIEEE Transactions on Signal Processing
Issue number3
Publication statusPublished - Mar 2008
Externally publishedYes


  • Adaptive non-Gaussian image denoising
  • Adaptive nonparametric regression
  • Anisotropic imaging
  • Fitted local likelihood (FLL)
  • Non-Gaussian denoising
  • Poissonian denoising
  • Varying threshold parameters


Dive into the research topics of 'Spatially adaptive estimation via fitted local likelihood techniques'. Together they form a unique fingerprint.

Cite this