Over the last 30 years a plethora of variational regularization models for image reconstruction have been proposed and thoroughly inspected by the applied mathematics community. Among them, the pioneering prototype often taught and learned in basic courses in mathematical image processing is the celebrated Rudin--Osher--Fatemi (ROF) model [L. I. Rudin, S. Osher, and E. Fatemi, Phys. D, 60 (1992), pp. 259--268], which relies on the minimization of the edge-preserving total variation (TV) seminorm as a regularization term. Despite its (often limiting) simplicity, this model is still very much employed in many applications and used as a benchmark for assessing the performance of modern learning-based image reconstruction approaches, thanks to its thorough analytical and numerical understanding. Among the many extensions to TV proposed over the years, a large class is based on the concept of space variance. Space-variant models can indeed overcome the intrinsic inability of TV to describe local features (strength, sharpness, directionality) by means of an adaptive mathematical modeling which accommodates local regularization weighting, variable smoothness, and anisotropy. Those ideas can further be cast in the flexible Bayesian framework of generalized Gaussian distributions and combined with maximum likelihood and hierarchical optimization approaches for efficient hyperparameter estimation. In this work, we review and connect the major contributions in the field of space-variant TV-type image reconstruction models, focusing, in particular, on their Bayesian interpretation which paves the way to new exciting and unexplored research directions.

We propose an automatic parameter selection strategy for the single image super-resolution problem for images corrupted by blur and additive white Gaussian noise with unknown standard deviation. The proposed approach exploits the structure of both the down-sampling and the blur operators in the frequency domain and computes the optimal regularisation parameter as the one optimising a suitably defined residual whiteness measure. Computationally, the proposed strategy relies on the fast solution of generalised Tikhonov $$\ell _2$$ℓ 2 – $$\ell _2$$ℓ 2 problems as proposed in Zhao et al. (IEEE Trans Image Process 25:3683–3697, 2016). These problems naturally appear as substeps of the Alternating Direction Method of Multipliers used to solve single image super-resolution problems with non-quadratic, non-smooth, sparsity-promoting regularisers both in convex and in non-convex regimes. After detailing the theoretical properties allowing to express the whiteness functional in a compact way, we report an exhaustive list of numerical experiments proving the effectiveness of the proposed approach for different type of problems, in comparison with well-known parameter selection strategies such as, e.g., the discrepancy principle.

A problem typically arising in imaging applications is the reconstruction task under sparsity constraints. A computationally efficient strategy to address this problem is to recast it in a hierarchical Bayesian framework coupled with a Maximum A Posteriori (MAP) estimation approach. More specifically, the original unknown is modeled as a conditionally Gaussian random variable with an unknown variance. Here, the expected behavior on the variance is encoded in a half-Cauchy hyperprior. The latter, coupled to the conditioned Gaussian prior, yields the horseshoe shrinkage prior, particularly popular within the statistics community and here introduced into the context of imaging problems. The arising non-convex MAP estimation problem is tackled via an alternating minimization scheme for which the global convergence to a stationary point is guaranteed. Experimental results prove that the derived hypermodel is competitive with classical variational methods as well as with other hierarchical Bayesian models typically employed for sparse recovery problems.

A common task in inverse problems and imaging is finding a solution that is sparse, in the sense that most of its components vanish. In the framework of compressed sensing, general results guaranteeing exact recovery have been proven. In practice, sparse solutions are often computed combining \begin{document}$ \ell_1 $\end{document}-penalized least squares optimization with an appropriate numerical scheme to accomplish the task. A computationally efficient alternative for finding sparse solutions to linear inverse problems is provided by Bayesian hierarchical models, in which the sparsity is encoded by defining a conditionally Gaussian prior model with the prior parameter obeying a generalized gamma distribution. An iterative alternating sequential (IAS) algorithm has been demonstrated to lead to a computationally efficient scheme, and combined with Krylov subspace iterations with an early termination condition, the approach is particularly well suited for large scale problems. Here the Bayesian approach to sparsity is extended to problems whose solution allows a sparse coding in an overcomplete system such as composite frames. It is shown that among the multiple possible representations of the unknown, the IAS algorithm, and in particular, a hybrid version of it, is effectively identifying the most sparse solution. Computed examples show that the method is particularly well suited not only for traditional imaging applications but also for dictionary learning problems in the framework of machine learning.

Images that have been contaminated by various kinds of blur and noise can be restored by the minimization of an $$\ell ^p$$ℓp - $$\ell ^q$$ℓq functional. The quality of the reconstruction depends on the choice of a regularization parameter. Several approaches to determine this parameter have been described in the literature. This work presents a numerical comparison of known approaches as well as of a new one.