Imaging through glass diffusers using densely connected convolutional networks

By Shuai Li, Mo Deng, Justin Lee, Ayan Sinha, George Barbastathis. Optica, 2017

345 citations recorded by the source corpus.

Computational imaging through scatter generally is accomplished by first characterizing the scattering medium so that its forward operator is obtained; and then imposing additional priors in the form of regularizers on the reconstruction functional so as to improve the condition of the originally ill-posed inverse problem. In the functional, the forward operator and regularizer must be entered explicitly or parametrically (e.g. scattering matrices and dictionaries, respectively.) However, the process of determining these representations is often incomplete, prone to errors, or infeasible. Recently, deep learning architectures have been proposed to instead learn both the forward operator and regularizer through examples. Here, we propose for the first time, to our knowledge, a convolutional neural network architecture called "IDiffNet" for the problem of imaging through diffuse media and demonstrate that IDiffNet has superior generalization capability through extensive tests with well-calibrated diffusers. We found that the Negative Pearson Correlation Coefficient loss function for training is more appropriate for spatially sparse objects and strong scattering conditions. Our results show that the convolutional architecture is robust to the choice of prior, as demonstrated by the use of multiple training and testing object databases, and capable of achieving higher space-bandwidth product reconstructions than previously reported.

Subfields: Acoustics and Ultrasonics, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ff7b655595c4d0a9a8e9a457b870ffbd328aa286

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

1. S. Rotter
2. Sylvain Gigan
3. Guohai Situ
4. Ori Katz
5. Meng Lyu
6. Hao Wang
7. Guowei Li
8. Y. Bromberg

In Biomedical Engineering

1. S. Rotter
2. Sylvain Gigan
3. Lei Tian
4. Ori Katz
5. Allard P. Mosk
6. Y. Bromberg
7. Laura Waller
8. Demetri Psaltis

In Computer Vision and Pattern Recognition

1. Lei Tian
2. Laura Waller
3. Allard P. Mosk
4. Demetri Psaltis
5. Hao Wang
6. Guohai Situ
7. Yujia Xue
8. Sylvain Gigan

Citations in the corpus

• Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media (2018, methodology): “Successful demonstrations of accomplishing this task via machine learning have been reported [15, 16, 31, 35].”
• Learning-based lensless imaging through optically thick scattering media (2019, methodology): “29 and 30 dealt with thin scattering layers like ground glass, through which the relationship between the acquired speckle and the target is easy to model owing to the memory effect.”
• Roadmap on wavefront shaping and deep imaging in complex media (2021, background): “The first successful demonstration of using DL to overcome the FoV limitation imposed by the memory effect (discussed in section 13) is shown in [131].”