Efficient and Robust Image Restoration Using Multiple-Feature L2-Relaxed Sparse Analysis Priors
|Title||Efficient and Robust Image Restoration Using Multiple-Feature L2-Relaxed Sparse Analysis Priors|
|Publication Type||Journal Article|
|Year of Publication||2015|
|Authors||Portilla, J., A. Tristán-Vega, and I. W. Selesnick|
|Journal||IEEE Transactions on Image Processing|
|Keywords||Bayes methods, Bayesian estimation, Convergence, Dictionaries, Estimation, Kernel, L2-relaxed L0 pseudo norm, L2-relaxed L0 pseudo-norm prior, L2-relaxed sparse analysis priors, Maximum likelihood estimation, Optimization, Redundancy, computational load, constrained dynamic method, deconvolution, deconvolution method, dynamically evolving parameters, estimation loop, fast constrained dynamic algorithm, image restoration, iterative marginal optimization, iterative methods, maximum a posteriori estimation, mean square error, mean square error methods, multiple representations, multiple-feature L2-relaxed sparse analysis priors, optimisation, robust tunable parameters, structural similarity terms|
We propose a novel formulation for relaxed analysis-based sparsity in multiple dictionaries as a general type of prior for images, and apply it for Bayesian estimation in image restoration problems. Our formulation of a ℓ2 -relaxed ℓ0 pseudo-norm prior allows for an especially simple maximum a posteriori estimation iterative marginal optimization algorithm, whose convergence we prove. We achieve a significant speedup over the direct (static) solution by using dynamically evolving parameters through the estimation loop. As an added heuristic twist, we fix in advance the number of iterations, and then empirically optimize the involved parameters according to two performance benchmarks. The resulting constrained dynamic method is not just fast and effective, it is also highly robust and flexible. First, it is able to provide an outstanding tradeoff between computational load and performance, in visual and objective, mean square error and structural similarity terms, for a large variety of degradation tests, using the same set of parameter values for all tests. Second, the performance benchmark can be easily adapted to specific types of degradation, image classes, and even performance criteria. Third, it allows for using simultaneously several dictionaries with complementary features. This unique combination makes ours a highly practical deconvolution method.