On the Use of Deep Learning for Three-Dimensional Computational Imaging

Barbastathis，George1,3; Pang，Subeen1; Kang，Iksung4; Wu，Ziling3; Liu，Zhiguang1; Guo，Zhen2; Zhang，Fucai5

10.1117/12.2655261

2023

0277-786X

1996-756X

Proceedings of SPIE - The International Society for Optical Engineering

12445

Deep learning has proven to be an efficient and robust method for many computational imaging systems. The advantages of machine learning, as a rule, are that it is fast-at least in its supervised form after training is complete-and seems exceedingly effective in capturing regularizing priors. Here, we focus the discussion on non-invasive three-dimensional (3D) object reconstruction. One then faces the additional dilemma of choosing the appropriate model of light-matter interaction inside the specimen, i.e. the forward operator. We describe the three stages of approximation that are applicable: weak scattering with weak diffraction (also known as the Radon transform), weak scattering with strong diffraction, and strong scattering. We then overview machine learning approaches for the various models, and glance at the consequences of oversimplifying the forward operator choice.

其他

英语

EI

Israeli Centers for Research Excellence[NRF2019-THE002-0006];

20232114124371

Computational Imaging ; Deep learning ; Imaging systems ; Learning systems

Ergonomics and Human Factors Engineering:461.4 ; Imaging Techniques:746

2-s2.0-85159716292

Scopus

1.Department of Mechanical Engineering,Massachusetts Institute of Technology,United States
2.Department of Electrical Engineering and Computer Science,Massachusetts Institute of Technology,United States
3.Singapore-MIT Alliance for Research & Technology Centre,Massachusetts Institute of Technology,United States
4.Department of Molecular and Cell Biology,University of California,Berkeley,United States
5.Department of Electrical Engineering,Southern University of Science and Technology,China

Barbastathis，George,Pang，Subeen,Kang，Iksung,et al. On the Use of Deep Learning for Three-Dimensional Computational Imaging[C],2023.