Lensless computational imaging through deep learning
Author(s)
Sinha, Ayan T; Lee, Justin; Li, Shuai; Barbastathis, George
Download1702.08516.pdf (14.30Mb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
Deep learning has been proven to yield reliably generalizable solutions to numerous classification and decision tasks. Here, we demonstrate for the first time to our knowledge that deep neural networks (DNNs) can be trained to solve end-to-end inverse problems in computational imaging. We experimentally built and tested a lensless imaging system where a DNN was trained to recover phase objects given their propagated intensity diffraction patterns.
Date issued
2017-09Department
Massachusetts Institute of Technology. Institute for Medical Engineering & Science; Massachusetts Institute of Technology. Department of Mechanical EngineeringJournal
Optica
Publisher
Optical Society of America
Citation
Sinha, Ayan et al. “Lensless Computational Imaging through Deep Learning.” Optica 4, 9 (September 2017): 1117 © 2017 Optical Society of America
Version: Original manuscript
ISSN
2334-2536