Optics Express· 2019Q1
Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging
- 326citations
- Q1SCImago
- 2019year
Short summary
A one-step end-to-end neural network trained solely on simulation data can reconstruct 2D images from 1D bucket signals in computational ghost imaging, eliminating the need for illumination pattern sequences.
AI-generated from the title and abstract; the full text is not read.
Key points
- A deep learning network can be trained using only simulation data for computational imaging tasks.
- A one-step end-to-end neural network reconstructs 2D images from 1D bucket signals in CGI.
- The trained network does not require the sequence of illumination patterns for image reconstruction.
- This method simplifies training data generation, especially for imaging through scattering media.
AI-generated from the title and abstract; the full text is not read.
Abstract
Artificial intelligence (AI) techniques such as deep learning (DL) for computational imaging usually require to experimentally collect a large set of labeled data to train a neural network. Here we demonstrate that a practically usable neural network for computational imaging can be trained by using simulation data. We take computational ghost imaging (CGI) as an example to demonstrate this method. We develop a one-step end-to-end neural network, trained with simulation data, to reconstruct two-dimensional images directly from experimentally acquired one-dimensional bucket signals, without the need of the sequence of illumination patterns. This is in particular useful for image transmission through quasi-static scattering media as little care is needed to take to simulate the scattering process when generating the training data. We believe that the concept of training using simulation data can be used in various DL-based solvers for general computational imaging.
The authors' abstract, as published at the source. Optics Express, 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Acoustics and Ultrasonics
Acoustics and UltrasonicsPhysics and Astronomy