A Caltech Library Service

Learning a Probabilistic Strategy for Computational Imaging Sensor Selection

Sun, He and Dalca, Adrian V. and Bouman, Katherine L. (2020) Learning a Probabilistic Strategy for Computational Imaging Sensor Selection. In: 2020 IEEE International Conference on Computational Photography (ICCP). IEEE , Piscataway, NJ, pp. 1-12. ISBN 9781728152301.

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Optimized sensing is important for computational imaging in low-resource environments, when images must be recovered from severely limited measurements. In this paper, we propose a physics-constrained, fully differentiable, autoencoder that learns a probabilistic sensor-sampling strategy for optimized sensor design. The proposed method learns a system's preferred sampling distribution that characterizes the correlations between different sensor selections as a binary, fully-connected Ising model. The learned probabilistic model is achieved by using a Gibbs sampling inspired network architecture, and is trained end-to-end with a reconstruction network for efficient co-design. The proposed framework is applicable to sensor selection problems in a variety of computational imaging applications. In this paper, we demonstrate the approach in the context of a very-long-baseline-interferometry (VLBI) array design task, where sensor correlations and atmospheric noise present unique challenges. We demonstrate results broadly consistent with expectation, and draw attention to particular structures preferred in the telescope array geometry that can be leveraged to plan future observations and design array expansions.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Dalca, Adrian V.0000-0002-8422-0136
Bouman, Katherine L.0000-0003-0077-4367
Additional Information:© 2020 IEEE. The authors would like to thank Lindy Blackburn, Alexander Raymond, Michael Johnson, and Sheperd Doeleman for helpful discussions on the constraints of a next-generation EHT array, and Michael Kellman for helpful discussions on Fourier ptychography. This work was supported by NSF award 1935980: “Next Generation Event Horizon Telescope Design,” and Beyond Limits.
Funding AgencyGrant Number
Subject Keywords:Computational Imaging, Optimized Sensing, Ising Model, Deep Learning, VLBI, Interferometry
Record Number:CaltechAUTHORS:20200605-134947553
Persistent URL:
Official Citation:H. Sun, A. V. Dalca and K. L. Bouman, "Learning a Probabilistic Strategy for Computational Imaging Sensor Selection," 2020 IEEE International Conference on Computational Photography (ICCP), Saint Louis, MO, USA, 2020, pp. 1-12, doi: 10.1109/ICCP48838.2020.9105133
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:103735
Deposited By: Tony Diaz
Deposited On:05 Jun 2020 21:06
Last Modified:03 Jun 2021 21:20

Repository Staff Only: item control page