Solving Inverse Problems with Model Mismatch using Untrained Neural Networks within Model-based Architectures

TL;DR

This paper introduces a novel approach that incorporates an untrained residual block into model-based deep learning architectures to effectively handle forward model mismatch in inverse problems, improving reconstruction quality without additional data.

Contribution

It proposes a unified, parameter-insensitive method with convergence guarantees that fits the forward model and reconstructs simultaneously, applicable to both linear and nonlinear inverse problems.

Findings

Significant artifact removal and detail preservation across applications.

Robustness to random initialization and increased iterations.

Effective in both linear and nonlinear inverse problems.

Abstract

Model-based deep learning methods such as loop unrolling (LU) and deep equilibrium model}(DEQ) extensions offer outstanding performance in solving inverse problems (IP). These methods unroll the optimization iterations into a sequence of neural networks that in effect learn a regularization function from data. While these architectures are currently state-of-the-art in numerous applications, their success heavily relies on the accuracy of the forward model. This assumption can be limiting in many physical applications due to model simplifications or uncertainties in the apparatus. To address forward model mismatch, we introduce an untrained forward model residual block within the model-based architecture to match the data consistency in the measurement domain for each instance. We propose two variants in well-known model-based architectures (LU and DEQ) and prove convergence under mild conditions. Our approach offers a unified solution that is less parameter-sensitive, requires no additional data, and enables simultaneous fitting of the forward model and reconstruction in a single pass, benefiting both linear and nonlinear inverse problems. The experiments show significant quality improvement in removing artifacts and preserving details across three distinct applications, encompassing both linear and nonlinear inverse problems. Moreover, we highlight reconstruction effectiveness in intermediate steps and showcase robustness to random initialization of the residual block and a higher number of iterations during evaluation. Code is available at \texttt{https://github.com/InvProbs/A-adaptive-model-based-methods}.