Back-Projection Based Fidelity Term for Ill-Posed Linear Inverse Problems

Abstract

Ill-posed linear inverse problems appear in many image processing applications, such as deblurring, superresolution and compressed sensing. Many restoration strategies involve minimizing a cost function, which is composed of fidelity and prior terms, balanced by a regularization parameter. While a vast amount of research has been focused on different prior models, the fidelity term is almost always chosen to be the least squares (LS) objective, that encourages fitting the linearly transformed optimization variable to the observations. In this work, we examine a different fidelity term, which has been implicitly used by the recently proposed iterative denoising and backward projections (IDBP) framework. This term encourages agreement between the projection of the optimization variable onto the row space of the linear operator and the pseudoinverse of the linear operator ("back-projection") applied on the observations. We analytically examine the difference between the two fidelity terms for Tikhonov regularization and identify cases where the new term has an advantage over the standard LS one. Moreover, we demonstrate empirically that the behavior of the two induced cost functions for sophisticated convex and nonconvex priors, such as total-variation, BM3D, and deep generative models, correlates with the obtained theoretical analysis.

Magnetoencephalography for epileptic focus localization based on Tucker decomposition with ripple window

“…Many algorithms were proposed to solve the ill‐posed problem in mathematical theories and other applications 18–20 . Over the past few decades, in the field of source location by MEG or EEG, the solutions of the ill‐posed problem were under different assumptions like multiple priors, especially “sparse” priors that make more feasible the source estimation 21 .…”

Efficient Image Reconstruction Algorithm for ECT System Using Local Ensemble Transform Kalman Filter

“…In the iterative techniques, the inverse and forward problems are solved in a continuous loop until an acceptable measurement error rate is reached. The Iterative Linear Back Projection (ILBP) is a standard procedure for building the images [31], [32]. Nevertheless, when a sharp transition exists between the different materials, the obtained images are blurred and suffer from a smoothing effect.…”

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

“…In such applications, denoising is a major challenge for the researchers [1]- [3]. Denoising is an inverse ill-posed problem [4] which is classically addressed by specifying a forward model and then invert it for the unknowns [5]. Recent developments are exploring the use of deep learning techniques for the denoising [6]- [10].…”