Prior Image-Constrained Reconstruction using Style-Based Generative Models
This work addresses a fundamental challenge in imaging science for applications like medical or scientific imaging, but it is incremental as it builds on existing deep learning and generative model methods.
The paper tackles the problem of reconstructing objects from incomplete imaging data by leveraging a known prior image, using a style-based generative model's latent space for optimization and constraints, and demonstrates superior performance in numerical experiments.
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.