Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Communications and Quantum Imaging

Time-efficient non-degenerate ghost imaging powered by deep learning

Chané Moodley, Bereneice Sephton, Valeria Rodríguez-Fajardo, Andrew Forbes

Published Jul 30, 2021• 1 citation
Publisher

Abstract

Quantum ghost imaging utilizes entangled photon pairs to enable an alternative image acquisition method. Information from either one of the photons does not allow for image reconstruction, however the image can be reconstructed by utilising the correlations that exist between the photon pair. Interestingly, these photon pairs can be either degenerate or non-degenerate in nature. Non-degenerate ghost imaging offers the ability to image with wavelength bandwidths where spatially resolving detectors are impractical, ineffective or expensive. Due to the scanning nature of spatially resolving detectors and the inherent low light levels of quantum experiments, imaging speeds are rather unsatisfactory. To overcome this limitation, we propose a two-step deep learning approach to establish an optimal early stopping point, tested on a non-degenerate system. In step one, we enhance the reconstructed image after each measurement by a deep convolution auto-encoder, followed by step two where a classifier is used to recognise the image. We achieved a recognition confidence of 75% at 20% of the image reconstruction time, hence reducing the image reconstruction time 5-fold while maintaining the image information. This, therefore, leads to a faster, more efficient image acquisition technique. Although tested on a non-degenerate system, our procedure can be extended to many such systems that are of quantum nature. We believe that this two-step deep learning approach will prove valuable to the community who are focusing their efforts on time-efficient ghost imaging.

DOI
10.1117/12.2594097

Related papers

Does quantum ghost imaging need a camera to image an object?

Chané Moodley, Andrew Forbes

Pairs of entangled photos are used to reconstruct an image in the application area known as quantum ghost imaging. It is the correlation between the photon pair that allows for the reconstruction of the image, as opposed to single photon detection. The entangled photons are spatially separated into two independent paths, one to illuminate the object and the other which is collected by a spatially resolving detector. Initially, ghost imaging experiments accomplished spatially resolving detectors by moving a single-pixel detector throughout a transverse scanning area. Advancements consisted of using ultra-sensitive cameras to avoid a system consisting of physically moving detectors. Ultra-sensitive cameras are, however, expensive and have limited spectral sensitivity. Here we demonstrate an alternative by utilising a spatial light modulator and a bucket detector to spatially resolve what is detected. Importantly, the masks displayed on the spatial light modulator must constitute a complete basis to acquire a completely reconstructed image. Historically, imaging speeds have been slow and inefficient due to the quadratic increase in the scanning capability for spatially resolved detectors and the low light levels associated with quantum experiments. Here we additionally utilise machine and deep learning algorithms to improve both image reconstruction time and resolution. We demonstrate this with a non-degenerate ghost imaging setup where the physical parameters such as the mask type and resolution are varied and controlled on a spatial light modulator. Thereby answering the question: can we image an object without using a camera?

•Sep 30, 2022•0 citations

Quantum imaging gets super smart

Chané Moodley, Andrew Forbes

Quantum ghost imaging is an alternative imaging technique which utilises pairs of entangled photons to reconstruct an image. Due to the scanning nature of spatially resolving detectors and the inherent low light levels of quantum experiments, imaging speeds are inefficient and scale quadratically with the required resolution. We leveraged artificial intelligence capabilities to achieve early object recognition and to super-resolve the reconstructed image. We achieved a 5x reduction in image acquisition times and super-resolved the images to a resolution 4x greater than the measured resolution. Leading to efficient image acquisition times without losing fine details of the image.

Quantum Communications and Quantum Imaging•Oct 4, 2022•0 citations

Super-resolved quantum ghost imaging

Chané Moodley, Andrew Forbes

Quantum ghost imaging offers many advantages over classical imaging, including low photon fluxes and non-degenerate object and image wavelengths for imaging light sensitive structures, but suffers from slow image reconstruction speeds. Image reconstruction times depend on the resolution of the required image which scale quadratically with the image resolution. Here, we propose a super-resolved imaging approach based on neural networks where we reconstruct a low resolution image, which we denoise and super-resolve to a high resolution image. To test the approach, we implemented both a generative adversarial network as well as a super-resolving autoencoder in conjunction with an experimental quantum ghost imaging setup, demonstrating its efficacy across a range of object and imaging projective mask types. We achieved super-resolving enhancement of [Formula: see text] the measured resolution with a fidelity close to 90[Formula: see text] at an acquisition time of N[Formula: see text] measurements, required for a complete N [Formula: see text] N pixel image solution. This significant resolution enhancement is a step closer to a common ghost imaging goal, to reconstruct images with the highest resolution and the shortest possible acquisition time.

Scientific Reports•Jun 20, 2022•32 citations

Fast correlated-photon imaging enhanced by deep learning

Zhanming Li, Shibao Wu, Jun Gao +5 more

Quantum imaging using photon pairs with strong quantum correlations has been harnessed to bring quantum advantages to various fields from biological imaging to range finding. Such inherent non-classical properties support the extraction of more valid signals to build photon-limited images, even in low-light conditions where the shot noise becomes dominant as light decreases to a single-photon level. Numerical optimization algorithms are possible but require thousands of photon-sparse frames, and they are thus unavailable in real time. We demonstrate fast correlated-photon imaging enhanced by deep learning as an intelligent computational strategy to discover a deeper structure in big data. Our work verifies that a convolutional neural network can efficiently solve inverse imaging problems associated with strong shot noise and background noise (electronic noise, scattered light). Our results show that we can overcome limitations due to the trade-off between imaging speed and image quality by pushing the low-light imaging technique to the single-photon level in real time, which enables deep-learning-enhanced quantum imaging for real-life applications.

Optica•Jan 13, 2021•35 citations

Quantum ghost imaging with a modal basis

Fazilah Nothlawala, Chané Moodley, Neelan Gounden +2 more

Quantum ghost imaging harnesses entangled photon pairs to form images using light that never directly interacts with the object. Conventional approaches rely on pixelated detectors or spatial masks, where the resolution is fundamentally limited by the pixel size and thus bounded by the Rayleigh criterion. In this work, we present a modal approach that replaces pixel-based detection with measurements in a basis of structured modes. By reconstructing images through tailored spatial modes, we decouple resolution from the physical limitations of detectors and instead tie it to the system’s optical precision and computational control. We demonstrate that even non-orthogonal modal sets can achieve high fidelity image reconstruction by exploiting modal sparsity, significantly reducing the number of required measurements. Using phase-only approximations of Hermite-Gaussian modes, we avoid the loss associated with complex amplitude modulation while retaining high reconstruction fidelity. The result is a high-resolution, high-efficiency quantum ghost imaging technique powered by structured light, opening new possibilities for photon-efficient imaging in low-light and quantum-limited regimes, such as biological microscopy and remote sensing.

Optical and Quantum Sensing and Precision Metrology II•Mar 5, 2026•0 citations

Entangled-photon compressive ghost imaging

Petros Zerom, Kam Wai Clifford Chan, John C. Howell +1 more

We have experimentally demonstrated high-resolution compressive ghost imaging at the single-photon level using entangled photons produced by a spontaneous parametric down-conversion source and using single-pixel detectors. For a given mean-squared error, the number of photons needed to reconstruct a two-dimensional image is found to be much smaller than that in quantum ghost imaging experiments employing a raster scan. This procedure not only shortens the data acquisition time, but also suggests a more economical use of photons for low-light-level and quantum image formation.

Physical Review A•Dec 27, 2011•102 citations
Quantum ghost imaging utilizes entangled photon pairs to enable an alternative image acquisition method. Information from either one of the photons does not allow for image reconstruction, however the image can be reconstructed by utilising the correlations that exist between the photon pair. Interestingly, these photon pairs can be either degenerate or non-degenerate in nature. Non-degenerate ghost imaging offers the ability to image with wavelength bandwidths where spatially resolving detectors are impractical, ineffective or expensive. Due to the scanning nature of spatially resolving detectors and the inherent low light levels of quantum experiments, imaging speeds are rather unsatisfactory. To overcome this limitation, we propose a two-step deep learning approach to establish an optimal early stopping point, tested on a non-degenerate system. In step one, we enhance the reconstructed image after each measurement by a deep convolution auto-encoder, followed by step two where a classifier is used to recognise the image. We achieved a recognition confidence of 75% at 20% of the image reconstruction time, hence reducing the image reconstruction time 5-fold while maintaining the image information. This, therefore, leads to a faster, more efficient image acquisition technique. Although tested on a non-degenerate system, our procedure can be extended to many such systems that are of quantum nature. We believe that this two-step deep learning approach will prove valuable to the community who are focusing their efforts on time-efficient ghost imaging.
Pairs of entangled photos are used to reconstruct an image in the application area known as quantum ghost imaging. It is the correlation between the photon pair that allows for the reconstruction of the image, as opposed to single photon detection. The entangled photons are spatially separated into two independent paths, one to illuminate the object and the other which is collected by a spatially resolving detector. Initially, ghost imaging experiments accomplished spatially resolving detectors by moving a single-pixel detector throughout a transverse scanning area. Advancements consisted of using ultra-sensitive cameras to avoid a system consisting of physically moving detectors. Ultra-sensitive cameras are, however, expensive and have limited spectral sensitivity. Here we demonstrate an alternative by utilising a spatial light modulator and a bucket detector to spatially resolve what is detected. Importantly, the masks displayed on the spatial light modulator must constitute a complete basis to acquire a completely reconstructed image. Historically, imaging speeds have been slow and inefficient due to the quadratic increase in the scanning capability for spatially resolved detectors and the low light levels associated with quantum experiments. Here we additionally utilise machine and deep learning algorithms to improve both image reconstruction time and resolution. We demonstrate this with a non-degenerate ghost imaging setup where the physical parameters such as the mask type and resolution are varied and controlled on a spatial light modulator. Thereby answering the question: can we image an object without using a camera?
Quantum ghost imaging is an alternative imaging technique which utilises pairs of entangled photons to reconstruct an image. Due to the scanning nature of spatially resolving detectors and the inherent low light levels of quantum experiments, imaging speeds are inefficient and scale quadratically with the required resolution. We leveraged artificial intelligence capabilities to achieve early object recognition and to super-resolve the reconstructed image. We achieved a 5x reduction in image acquisition times and super-resolved the images to a resolution 4x greater than the measured resolution. Leading to efficient image acquisition times without losing fine details of the image.
Quantum ghost imaging offers many advantages over classical imaging, including low photon fluxes and non-degenerate object and image wavelengths for imaging light sensitive structures, but suffers from slow image reconstruction speeds. Image reconstruction times depend on the resolution of the required image which scale quadratically with the image resolution. Here, we propose a super-resolved imaging approach based on neural networks where we reconstruct a low resolution image, which we denoise and super-resolve to a high resolution image. To test the approach, we implemented both a generative adversarial network as well as a super-resolving autoencoder in conjunction with an experimental quantum ghost imaging setup, demonstrating its efficacy across a range of object and imaging projective mask types. We achieved super-resolving enhancement of [Formula: see text] the measured resolution with a fidelity close to 90[Formula: see text] at an acquisition time of N[Formula: see text] measurements, required for a complete N [Formula: see text] N pixel image solution. This significant resolution enhancement is a step closer to a common ghost imaging goal, to reconstruct images with the highest resolution and the shortest possible acquisition time.
Quantum imaging using photon pairs with strong quantum correlations has been harnessed to bring quantum advantages to various fields from biological imaging to range finding. Such inherent non-classical properties support the extraction of more valid signals to build photon-limited images, even in low-light conditions where the shot noise becomes dominant as light decreases to a single-photon level. Numerical optimization algorithms are possible but require thousands of photon-sparse frames, and they are thus unavailable in real time. We demonstrate fast correlated-photon imaging enhanced by deep learning as an intelligent computational strategy to discover a deeper structure in big data. Our work verifies that a convolutional neural network can efficiently solve inverse imaging problems associated with strong shot noise and background noise (electronic noise, scattered light). Our results show that we can overcome limitations due to the trade-off between imaging speed and image quality by pushing the low-light imaging technique to the single-photon level in real time, which enables deep-learning-enhanced quantum imaging for real-life applications.
Quantum ghost imaging harnesses entangled photon pairs to form images using light that never directly interacts with the object. Conventional approaches rely on pixelated detectors or spatial masks, where the resolution is fundamentally limited by the pixel size and thus bounded by the Rayleigh criterion. In this work, we present a modal approach that replaces pixel-based detection with measurements in a basis of structured modes. By reconstructing images through tailored spatial modes, we decouple resolution from the physical limitations of detectors and instead tie it to the system’s optical precision and computational control. We demonstrate that even non-orthogonal modal sets can achieve high fidelity image reconstruction by exploiting modal sparsity, significantly reducing the number of required measurements. Using phase-only approximations of Hermite-Gaussian modes, we avoid the loss associated with complex amplitude modulation while retaining high reconstruction fidelity. The result is a high-resolution, high-efficiency quantum ghost imaging technique powered by structured light, opening new possibilities for photon-efficient imaging in low-light and quantum-limited regimes, such as biological microscopy and remote sensing.
We have experimentally demonstrated high-resolution compressive ghost imaging at the single-photon level using entangled photons produced by a spontaneous parametric down-conversion source and using single-pixel detectors. For a given mean-squared error, the number of photons needed to reconstruct a two-dimensional image is found to be much smaller than that in quantum ghost imaging experiments employing a raster scan. This procedure not only shortens the data acquisition time, but also suggests a more economical use of photons for low-light-level and quantum image formation.