An unsupervised deep learning algorithm for single-site reconstruction in quantum gas microscopes
Abstract
In quantum gas microscopy experiments, reconstructing the site-resolved lattice occupation with high fidelity is essential for the accurate extraction of physical observables. For short interatomic separations and limited signal-to-noise ratio, this task becomes increasingly challenging. Common methods rapidly decline in performance as the lattice spacing is decreased below half the imaging resolution. Here, we present a novel algorithm based on deep convolutional neural networks to reconstruct the site-resolved lattice occupation with high fidelity. The algorithm can be directly trained in an unsupervised fashion with experimental fluorescence images and allows for a fast reconstruction of large images containing several thousand lattice sites. We benchmark its performance using a quantum gas microscope with cesium atoms that utilizes short-spaced optical lattices with lattice constant nm and a typical Rayleigh resolution of nm. We obtain promising reconstruction fidelities~ across all fillings based on a statistical analysis. We anticipate this algorithm to enable novel experiments with shorter lattice spacing, boost the readout fidelity and speed of lower-resolution imaging systems, and furthermore find application in related experiments such as trapped ions.
Keywords
Cite
@article{arxiv.2212.11974,
title = {An unsupervised deep learning algorithm for single-site reconstruction in quantum gas microscopes},
author = {Alexander Impertro and Julian F. Wienand and Sophie Häfele and Hendrik von Raven and Scott Hubele and Till Klostermann and Cesar R. Cabrera and Immanuel Bloch and Monika Aidelsburger},
journal= {arXiv preprint arXiv:2212.11974},
year = {2023}
}