CaltechAUTHORS
  A Caltech Library Service

Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging

Sun, He and Bouman, Katherine L. (2021) Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging. In: Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). Proceedings of the AAAI Conference on Artificial Intelligence. Vol.35. Association for the Advancement of Artificial Intelligence , Palo Alto, CA, pp. 2628-2637. https://resolver.caltech.edu/CaltechAUTHORS:20210604-142552450

[img] PDF - Accepted Version
See Usage Policy.

15MB
[img] PDF - Supplemental Material
See Usage Policy.

9MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210604-142552450

Abstract

Computational image reconstruction algorithms generally produce a single image without any measure of uncertainty or confidence. Regularized Maximum Likelihood (RML) and feed-forward deep learning approaches for inverse problems typically focus on recovering a point estimate. This is a serious limitation when working with under-determined imaging systems, where it is conceivable that multiple image modes would be consistent with the measured data. Characterizing the space of probable images that explain the observational data is therefore crucial. In this paper, we propose a variational deep probabilistic imaging approach to quantify reconstruction uncertainty. Deep Probabilistic Imaging (DPI) employs an untrained deep generative model to estimate a posterior distribution of an unobserved image. This approach does not require any training data; instead, it optimizes the weights of a neural network to generate image samples that fit a particular measurement dataset. Once the network weights have been learned, the posterior distribution can be efficiently sampled. We demonstrate this approach in the context of interferometric radio imaging, which is used for black hole imaging with the Event Horizon Telescope, and compressed sensing Magnetic Resonance Imaging (MRI).


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://ojs.aaai.org/index.php/AAAI/article/view/16366PublisherArticle
https://arxiv.org/abs/2010.14462arXivDiscussion Paper
ORCID:
AuthorORCID
Sun, He0000-0003-1526-6787
Bouman, Katherine L.0000-0003-0077-4367
Additional Information:© 2021 Association for the Advancement of Artificial Intelligence. Published 2021-05-18. This work was supported by NSF award 1935980: Next Generation Event Horizon Telescope Design, and Beyond Limits. The authors would also like to thank Joe Marino, Dominic Pesce, S. Kevin Zhou, and Tianwei Yin for the helpful discussions.
Group:Astronomy Department
Funders:
Funding AgencyGrant Number
NSFAST-1935980
Beyond LimitsUNSPECIFIED
Subject Keywords:Computational Photography, Image & Video Synthesis
Series Name:Proceedings of the AAAI Conference on Artificial Intelligence
Record Number:CaltechAUTHORS:20210604-142552450
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210604-142552450
Official Citation:Sun, H., & Bouman, K. L. (2021). Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2628-2637.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:109398
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:07 Jun 2021 14:19
Last Modified:14 Sep 2021 17:29

Repository Staff Only: item control page