Lensless computational imaging through deep learning
Massachusetts Institute of Technology · Singapore-MIT Alliance for Research and Technology
Indexed incrossrefdoaj
Abstract
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.
Citation impact
698
total citations
- FWCI
- 47.39
- Percentile
- 100%
- References
- 54
Citations per year
Authors
4Topics & keywords
Topics
Keywords
- Computer science
- Deep learning
- Artificial intelligence
- Deep neural networks
- Inverse problem
- Artificial neural network
- Computer vision
- Machine learning
UN Sustainable Development Goals
- Peace, Justice and strong institutions
No related works found for this paper.
Funding
- UDU.S. Department of EnergyAwards: FG02-97ER25308, DE-FG02-97ER25308, DE-FG02-, DE-FG02
- NRNational Research Foundation
- NRNational Research Foundation Singapore
- SASingapore-MIT Alliance for Research and Technology Centre
- ARAdvanced Research Projects Agency
- IAIntelligence Advanced Research Projects Activity