On the use of deep learning for computational imaging

On the use of deep learning for computational imaging

Show other versions (1)

© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. Deep learning has emerged as a class of optimization algorithms proven to be effective for a variety of inference and decision tasks. Similar algorithms, with appropriate modifications, have also been widely adopted fo...

Full description

Bibliographic Details
Main Author: Barbastathis, George (Author)
Other Authors: Massachusetts Institute of Technology. Department of Mechanical Engineering (Contributor), Singapore-MIT Alliance in Research and Technology (SMART) (Contributor)
Format: Article
Language:English
Published: SPIE-Intl Soc Optical Eng, 2021-12-13T19:37:42Z.
Subjects:
Article
Online Access:Get fulltext
LEADER 01215 am a22001813u 4500
001 138459.2
042 |a dc 
100 1 0 |a Barbastathis, George  |e author 
100 1 0 |a Massachusetts Institute of Technology. Department of Mechanical Engineering  |e contributor 
100 1 0 |a Singapore-MIT Alliance in Research and Technology   |q  (SMART)   |e contributor 
245 0 0 |a On the use of deep learning for computational imaging 
260 |b SPIE-Intl Soc Optical Eng,   |c 2021-12-13T19:37:42Z. 
856 |z Get fulltext  |u https://hdl.handle.net/1721.1/138459.2 
520 |a © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. Deep learning has emerged as a class of optimization algorithms proven to be effective for a variety of inference and decision tasks. Similar algorithms, with appropriate modifications, have also been widely adopted for computational imaging. Here, we review the basic tenets of deep learning and computational imaging, and overview recent progress in two applications: super resolution and phase retrieval. 
546 |a en 
655 7 |a Article 
773 |t 10.1117/12.2571322 
773 |t Proceedings of SPIE - The International Society for Optical Engineering 

Similar Items