[Paper] [Code] [Talk]

Obtaining an accurate and reliable 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.

The above image shows the ground truth, prior image and images reconstructed from simulated MRI measurements. It can be seen that since StyleGAN2 is better able to capture the differences between the ground truth and the prior image, it shows superior performance.

Publications:

1. Kelkar, V. A., & Anastasio, M. A. (2021). Prior Image-Constrained Reconstruction using Style-Based Generative Models. Proceedings of the 38th International Conference on Machine Learning (ICML).