Fast Correlated-Photon Imaging Enhanced by Deep Learning

TL;DR

This paper demonstrates a real-time, deep learning-enhanced correlated-photon imaging technique that effectively reconstructs high-quality images at the single-photon level, overcoming shot noise and enabling practical quantum imaging applications.

Contribution

It introduces a convolutional neural network approach to rapidly reconstruct images in low-light, photon-limited conditions, bridging the gap between imaging speed and quality.

Findings

Achieved real-time image reconstruction at single-photon levels.

Effectively suppresses shot noise and background noise.

Enables practical quantum imaging applications.

Abstract

Correlated photon pairs, carrying strong quantum correlations, have been harnessed to bring quantum advantages to various fields from biological imaging to range finding. Such inherent non-classical properties support extracting more valid signals to build photon-limited images even in low flux-level, where the shot noise becomes dominant as light source decreases to single-photon level. Optimization by numerical reconstruction algorithms is possible but require thousands of photon-sparse frames, thus unavailable in real time. Here, we present an experimental fast correlated-photon imaging enhanced by deep learning, showing an intelligent computational strategy to discover deeper structure in big data. Convolutional neural network is found being able to efficiently solve image inverse problems associated with strong shot noise and background noise (electronic noise, scattered light). Our results fill the key gap in incompatibility between imaging speed and image quality by pushing low-light imaging technique to the regime of real-time and single-photon level, opening up an avenue to deep leaning-enhanced quantum imaging for real-life applications.