Abstract

Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of scattering conditions, individual “expert” networks need to be trained for each condition. However, the expert’s performance sharply degrades when the testing condition differs from the training. An alternative brute-force approach is to train a “generalist” network using data from diverse scattering conditions. It generally requires a larger network to encapsulate the diversity in the data and a sufficiently large training set to avoid overfitting. Here, we propose an adaptive learning framework, termed dynamic synthesis network (DSN), which dynamically adjusts the model weights and adapts to different scattering conditions. The adaptability is achieved by a novel “mixture of experts” architecture that enables dynamically synthesizing a network by blending multiple experts using a gating network. We demonstrate the DSN in holographic 3D particle imaging for a variety of scattering conditions. We show in simulation that our DSN provides generalization across a continuum of scattering conditions. In addition, we show that by training the DSN entirely on simulated data, the network can generalize to experiments and achieve robust 3D descattering. We expect the same concept can find many other applications, such as denoising and imaging in scattering media. Broadly, our dynamic synthesis framework opens up a new paradigm for designing highly adaptive deep learning and computational imaging techniques.

We demonstrate a dynamic synthesis deep learning framework to adaptively adjusts model weights and adapts to different scattering conditions, which opens up a new paradigm for adaptive computational imaging.

Details

Title
Adaptive 3D descattering with a dynamic synthesis network
Author
Tahir Waleed 1   VIAFID ORCID Logo  ; Wang, Hao 1 ; Tian Lei 2   VIAFID ORCID Logo 

 Boston University, Department of Electrical and Computer Engineering, Boston, USA (GRID:grid.189504.1) (ISNI:0000 0004 1936 7558) 
 Boston University, Department of Electrical and Computer Engineering, Boston, USA (GRID:grid.189504.1) (ISNI:0000 0004 1936 7558); Boston University, Department of Biomedical Engineering, Boston, USA (GRID:grid.189504.1) (ISNI:0000 0004 1936 7558) 
Publication year
2022
Publication date
2022
Publisher
Springer Nature B.V.
e-ISSN
20477538
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2632478301
Copyright
© The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.