DO-CGI: deep-optimized illumination patterns for computational ghost imaging at low sampling ratios

2026/07/28 by Mor Hale, Ofir Lindenbaum, Eliahu Cohen
Physics and Astronomy · #physics.optics

paper · pdf

12 pages, 8 figures, comments are welcome!

arxiv created 2026/07/28 · arxiv updated 2026/07/30

Abstract

Computational ghost imaging (CGI) reconstructs objects from known illumination patterns and bucket-detector measurements, but quality deteriorates at low sampling ratios (SRs). We present a deep-learning framework that optimizes grayscale diffuser patterns before reconstruction. In simulations using CIFAR-10 and MNIST images with Split Bregman reconstruction, the learned patterns outperform random patterns in peak signal-to-noise ratio and structural similarity, including at SRs below 5%. Patterns trained on CIFAR-10 also transfer to MNIST and remain effective under moderate perturbations of the sensing matrix. These results support learned pattern design as a route to fewer CGI measurements.

Citations

• Deep Learning in Classical X-ray Ghost Imaging for Dose Reduction
• Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit

Related

• Fast Computational Ghost Imaging using Unpaired Deep Learning and a Constrained Generative Adversarial Network
• Large model enhanced computational ghost imaging
• Improvements of computational ghost imaging by using Special-Hadamard patterns
• Ghost Image Processing
• Noise2Ghost: Self-supervised deep convolutional reconstruction for ghost imaging