Alexandre Goy

Alexandre Goy

Auto-generated profile, based on publicly available information

Alexandre Goy

Mechanical Engineering Massachusetts Institute of Technology MA02139 Cambridge USA.

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2018 in Physical Review Letters
Verified
Journal Article
Open access
PDF file
AGAlexandre Goy
Alexandre Goy
KAKwabena Arthur
Kwabena Arthur
SLShuai Li
Shuai Li
GBGeorge Barbastathis
George Barbastathis
Imaging systems’ performance at low light intensity is affected by shot noise, which becomes increasingly strong as the power of the light source decreases. In this Letter, we experimentally demonstrate the use of deep neural networks to recover objects illuminated with weak light and demonstrate better performance than with the classical Gerchberg-Saxton phase retrieval algorithm for equivalent signal over noise ratio. The prior contained in the training image set can be leveraged by the deep neural network to detect features with a signal over noise ratio close to one. We apply this principle to a phase retrieval problem and show successful recovery of the object’s most salient features with as little as one photon per detector pixel on average in the illumination beam. We also show that the phase reconstruction is significantly improved by training the neural network with an initial estimate of the object, as opposed to training it with the raw intensity measurement.

19 December 2018 in arXiv
Verified
Preprint
Open access
PDF file
AGAlexandre Goy
Alexandre Goy
GRGirish Rughoobur
Girish Rughoobur
SLShuai Li
Shuai Li
KAKwabena Arthur
Kwabena Arthur
AAAkintunde I. Akinwande
Akintunde I. Akinwande
GBGeorge Barbastathis
George Barbastathis
We present a Machine Learning-based method for tomographic reconstruction of dense layered objects, with range of projection angles limited to $\pm $10$^\circ$. Whereas previous approaches to phase tomography generally require two steps, first to retrieve phase projections from intensity projections and then perform tomographic reconstruction on the retrieved phase projections, in our work a physics-informed pre-processor followed by a Deep Neural Network (DNN) conduct the three-dimensional reconstruction directly from the intensity projections. We demonstrate this single-step method experimentally in the visible optical domain on a scaled up integrated circuit phantom. We show that even under conditions of highly attenuated photon fluxes a DNN trained only on synthetic data can be used to successfully reconstruct physical samples disjoint from the synthetic training set. Thus, the need of producing a large number of physical examples for training is ameliorated. The method is generally applicable to tomography with electromagnetic or other types of radiation at all bands.

1 January 2018
Verified
Conference Paper
Closed access
PDF file
AGAlexandre Goy
Alexandre Goy
KAKwabena Arthur
Kwabena Arthur
SLShuai Li
Shuai Li
GBGeorge Barbastathis
George Barbastathis
Poisson noise due to the quantization of light is a universal phenomenon, especially severe in low light imaging conditions. Such noise is unavoidable and impacts computational imaging systems and algorithms. In this paper, we show how to efficiently use deep neural networks to handle Poisson noise in the context of a phase retrieval problem. For sparse objects, we demonstrate successful phase recovery with as little as 10 photons per detector pixel per acquisition cycle.

1 January 2018
Verified
Conference Paper
Closed access
PDF file
GBGeorge Barbastathis
George Barbastathis
AGAlexandre Goy
Alexandre Goy
KAKwabena Arthur
Kwabena Arthur
MDMo Deng
Mo Deng
SLShuai Li
Shuai Li
Deep Learning presents a promising opportunity to design computational architectures for solving inverse problems. In this talk, we will present several approaches for performing computational imaging in this fashion, and discuss their relative merits especially with respect to image fidelity and robustness to noise.

12 June 2019 in arXiv
Verified
Preprint
Open access
PDF file
MDMo Deng
Mo Deng
AGAlexandre Goy
Alexandre Goy
SLShuai Li
Shuai Li
KAKwabena Arthur
Kwabena Arthur
GBGeorge Barbastathis
George Barbastathis
Deep neural networks (DNNs) are efficient solvers for ill-posed problems and have been shown to outperform classical optimization techniques in several computational imaging problems. DNNs are trained by solving an optimization problem implies the choice of an appropriate loss function, i.e., the function to optimize. In a recent paper [A. Goy \textit{et al.}, Phys. Rev. Lett. 121(24), 243902 (2018)], we showed that DNNs trained with the negative Pearson correlation coefficient as the loss function are particularly fit for photon-starved phase retrieval problems, which are fundamentally affected by strong Poison noise. In this paper we demonstrate that the use of a perceptual loss function significantly improves the reconstructions.