Prior Image-Constrained Reconstruction using Style-Based Generative Models

TL;DR

This paper introduces a novel image reconstruction framework that leverages style-based generative models and a known prior image to improve recovery from incomplete measurements, with theoretical analysis and superior experimental results.

Contribution

It proposes a new optimization approach in the latent space of style-based generative models that incorporates prior image constraints for improved reconstruction.

Findings

Stable recovery is theoretically supported.

Outperforms related methods in numerical experiments.

Effective for highly incomplete imaging measurements.

Abstract

Obtaining a useful estimate of an object from highly incomplete imaging measurements remains a holy grail of imaging science. Deep learning methods have shown promise in learning object priors or constraints to improve the conditioning of an ill-posed imaging inverse problem. In this study, a framework for estimating an object of interest that is semantically related to a known prior image, is proposed. An optimization problem is formulated in the disentangled latent space of a style-based generative model, and semantically meaningful constraints are imposed using the disentangled latent representation of the prior image. Stable recovery from incomplete measurements with the help of a prior image is theoretically analyzed. Numerical experiments demonstrating the superior performance of our approach as compared to related methods are presented.