Single Pixel Imaging and Compressive Sensing: A Practical Tutorial

TL;DR

This tutorial explains single pixel imaging and compressive sensing, highlighting their practical implementation, benefits in low-cost and noisy environments, and demonstrating reconstruction methods including deep learning.

Contribution

It provides a comprehensive guide on implementing single pixel imaging and compressive sensing with practical algorithms and Python notebooks for reproducibility.

Findings

Effective measurement bases for single pixel imaging

Comparison of deterministic and deep learning reconstruction methods

Enhanced imaging in noisy and low-light conditions

Abstract

Single Pixel Imaging is an emerging imaging technique that employs a bucket detector (photodiode) to sample a spatially modulated light field, rather than measuring the spatial distribution with an array of detectors. This approach provides a low-cost alternative for imaging at unconventional wavelengths and enables improved signal collection in noisy measurement environments. Furthermore, it allows the application of compressive sensing to reduce the amount of acquired data and measurement time, facilitating live or in vivo imaging applications. This tutorial presents the experimental implementation of measurement bases and compressive sensing reconstruction methods, including both deterministic algorithms and deep learning approaches. Accompanying Python notebooks guide readers through the reproduction of the presented results and support the application of the methods to their own work.