Open Access
Add to BibSonomyAbstract
We present a deep learning approach to capture coherent light propagation through free space and invert it so as to obtain images of phase objects from the scattered intensity. The method seems to generalize well even when trained on specific databases, e.g. of faces.
© 2017 Optical Society of America
PDF ArticleMore Like This
Solving inverse problems using residual neural networks
Ayan Sinha, Justin Lee, Shuai Li, and George Barbastathis
W1A.3 Digital Holography and Three-Dimensional Imaging (DH) 2017
Solving Inverse Problems using Self-Supervised Deep Neural Nets
Jiapeng Liu, Muralidhar M. Balaji, Christopher A. Metzler, M. Salman Asif, and Prasanna Rangarajan
CTh5A.2 Computational Optical Sensing and Imaging (COSI) 2021
Application of deep learning to direct and inverse problems in plasmonic coloring
Josh Baxter, Antonino Calà Lesina, Jean-Michel Guay, Arnaud Weck, Pierre Berini, and Lora Ramunno
FTu4C.4 CLEO: QELS_Fundamental Science (CLEO:FS) 2019