Fast Computational Ghost Imaging using Unpaired Deep Learning and a Constrained Generative Adversarial Network

TL;DR

This paper introduces a fast deep learning method using a constrained Wasserstein GAN for high-quality ghost image reconstruction from low SNR images without requiring paired training data.

Contribution

It presents a novel unpaired deep learning approach with a regularized GAN to improve ghost imaging speed and quality in low SNR conditions.

Findings

Effective reconstruction of high SNR images from low SNR ghost images.

The method performs well even when test images have different SNR levels from training.

Regularization enforces faithful image generation in low-noise manifolds.

Abstract

The unpaired training can be the only option available for fast deep learning-based ghost imaging, where obtaining a high signal-to-noise ratio (SNR) image copy of each low SNR ghost image could be practically time-consuming and challenging. This paper explores the capabilities of deep learning to leverage computational ghost imaging when there is a lack of paired training images. The deep learning approach proposed here enables fast ghost imaging through reconstruction of high SNR images from faint and hastily shot ghost images using a constrained Wasserstein generative adversarial network. In the proposed approach, the objective function is regularized to enforce the generation of faithful and relevant high SNR images to the ghost copies. This regularization measures the distance between reconstructed images and the faint ghost images in a low-noise manifold generated by a shadow network. The performance of the constrained network is shown to be particularly important for ghost images with low SNR. The proposed pipeline is able to reconstruct high-quality images from the ghost images with SNR values not necessarily equal to the SNR of the training set.