Lensless computational imaging through deep learning
By Ayan Sinha, Justin Lee, Shuai Li, George Barbastathis. arXiv.org, 2017
588 citations recorded by the source corpus.
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.
Subfields: Acoustics and Ultrasonics, Atomic and Molecular Physics, and Optics, Media Technology
View Paper: https://www.semanticscholar.org/paper/d8bf4cac5e5984457e5c8570cfa35f79ebfddd57
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Acoustics and Ultrasonics
- Rebecca M. Willett
- Guohai Situ
- Meng Lyu
- Hao Wang
- Guowei Li
- Richard Baraniuk
- A. Dimakis
- David A. B. Miller
In Atomic and Molecular Physics, and Optics
- Marin Soljačić
- Shanhui Fan
- Dirk Englund
- Aydogan Ozcan
- David A. B. Miller
- Gordon Wetzstein
- Demetri Psaltis
- Sylvain Gigan
In Media Technology
- Richard Baraniuk
- Ramesh Raskar
- Rebecca M. Willett
- A. Dimakis
- Gordon Wetzstein
- Guohai Situ
- Sylvain Gigan
- Aydogan Ozcan
Citations in the corpus
- Fringe pattern analysis using deep learning (2018, unknown): “10,11 In this letter, we demonstrate experimentally for the first time, to our knowledge, that the use of a deep neural network can substantially enhance the accuracy of phase demodulation from a single fringe pattern.”
- PhaseStain: the digital staining of label-free quantitative phase microscopy images using deep learning (2018, methodology): “…based on a data-driven approach, solving inverse problems in optics, such as super-resolution 15 – 17 , holographic image reconstruction and phase recovery 18 – 21 , tomography 22 , Fourier ptycho-graphic microscopy 23 , localization microscopy 24 – 26 , and ultrashort pulse reconstruction 27 .”
- Deep-learning-based ghost imaging (2017, methodology): “For example, people have used it in fluorescence lifetime imaging 24 phase imaging 25,26 and imaging through scattering media 27,28 By combining GI and DL, we show in this manuscript that GIDL can also decrease the number of measurements significantly as CSGI, but with much better reconstruction.”
- Flash Photography for Data-Driven Hidden Scene Recovery (2018, methodology): “Data-driven techniques have also been applied to problems in the computational imaging community such as phase imaging [34], compressive imaging [25], tomography [22], microscopy [18], imaging [17], and imaging through scattering media [31].”
- On the use of deep learning for computational imaging (2020, unknown): “(c) Pre-processor or (d) End-to-End architecture.(2,26) “Approximant” architecture.”
- Learning-based lensless imaging through optically thick scattering media (2019, unknown): “27 Surprisingly, in the case of imaging through thick scattering media, we found that the HNN trained by the digital images alone can retrieve the images of handwritten English letters, which were manually written by one of the authors.”
- Deep Learning Techniques for Inverse Problems in Imaging (2020, background): “ing [45], holography [46], [47], ghost imaging [48], imaging through scattering media [49]–[51], and non-line-of-sight imaging [52], which is illustrated in Figure 5.”
- Inference in artificial intelligence with deep optics and photonics (2020, background): “…the amplitude terms are most relevant and blue whenever the phase terms dominate. freeform lenses for extended depth of field 65 , image classification 13–15 , flat cameras 72 , high dynamic range imaging 73 , wavelength demultiplexing 74 , or depth sensing with conventional 2D cameras 75–77 .”