Abstract
We propose a neural network regularizer that mitigates the ill-conditionedness of the Lippmann-Schwinger equation. By learning the physics, it can significantly reduce the computational time and can be generalizable to objects unseen during the training.
© 2023 The Author(s)
PDF ArticleMore Like This
Subeen Pang and George Barbastathis
CTh4D.4 Computational Optical Sensing and Imaging (COSI) 2023
Ayan Sinha, Justin Lee, Shuai Li, and George Barbastathis
W1A.3 Digital Holography and Three-Dimensional Imaging (DH) 2017
Bo Liu, Christian Bluemm, Stefano Calabrò, Bing Li, and Ulf Schlichtmann
M1F.5 Optical Fiber Communication Conference (OFC) 2023