optics

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

arXiv:2607.26216

summary

The paper introduces a deep‑learning framework that designs optimized illumination patterns for computational ghost imaging, achieving higher image quality at very low sampling ratios.

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.

12 pages, 8 figures, comments are welcome!

Topics & keywords

#computational ghost imaging#deep learning#pattern optimization#low sampling ratio#image reconstructiondeep‑optimized illumination patternssplit Bregman reconstructionpeak signal‑to‑noise ratiostructural similarityCIFAR‑10MNIST
DO-CGI: deep-optimized illumination patterns for computational ghost imaging at low sampling ratios · wovepaper