Statistical Multiresolution Estimation in Imaging: Fundamental Concepts and Algorithmic Framework
Preprint
Abstract
In this paper we introduce a general class of statistical multiresolution estimators and develop an algorithmic framework for computing those. By this we mean estimators that are defined as solutions of convex optimization problems with $\ell_\infty$-type constraints. We employ a combination of an alternating direction augmented Lagrangian technique with Dykstra's algorithm for computing orthogonal projections onto intersections of convex sets. The capability of the proposed method is illustrated by various examples from imaging.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- An alternating direction method for finding Dantzig selectorsComputational Statistics & Data Analysis, 2012
- Locally adaptive image denoising by a statistical multiresolution criterionComputational Statistics & Data Analysis, 2012
- Templates for convex cone problems with applications to sparse signal recoveryMathematical Programming Computation, 2011
- Extremes of the standardized Gaussian noiseStochastic Processes and their Applications, 2011
- Automated Regularization Parameter Selection in Multi-Scale Total Variation Models for Image RestorationJournal of Mathematical Imaging and Vision, 2010
- Shao's theorem on the maximum of standardized random walk increments for multidimensional arraysESAIM: Probability and Statistics, 2009
- The Equivalence of the Taut String Algorithm and BV-RegularizationJournal of Mathematical Imaging and Vision, 2006
- TV Based Image Restoration with Local ConstraintsJournal of Scientific Computing, 2003
- The rate of convergence of dykstra's cyclic projections algorithm: The polyhedral caseNumerical Functional Analysis and Optimization, 1994
- A cyclic projection algorithm via dualityMetrika, 1989