ICML 2021spotlight33 citations

Prior Image-Constrained Reconstruction using Style-Based Generative Models

Varun A Kelkar, Mark Anastasio

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.

BibTeX
@InProceedings{pmlr-v139-kelkar21a,
  title = 	 {Prior Image-Constrained Reconstruction using Style-Based Generative Models},
  author =       {Kelkar, Varun A and Anastasio, Mark},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {5367--5377},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/kelkar21a/kelkar21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/kelkar21a.html},
  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.}
}
Prior Image-Constrained Reconstruction using Style-Based Generative Models · ICML 2021