Comprehensive compensation of real-world degradations for robust single-pixel imaging

TL;DR

This paper introduces a new method to improve image quality in single-pixel imaging by accounting for real-world noise and degradation.

Contribution

The paper proposes a novel degradation model and a deep-blind neural network for robust single-pixel imaging without needing degradation parameters.

Findings

A comprehensive degradation model for single-pixel imaging is developed.

A deep-blind network significantly improves image reconstruction at ultra-low sampling rates.

The method generalizes well across various degradation conditions.

Abstract

Single-pixel imaging (SPI) faces significant challenges in reconstructing high-quality images under complex real-world degradation conditions. This paper presents an innovative degradation model for the physical processes in SPI, providing the first comprehensive and quantitative analysis of various SPI noise sources encountered in real-world applications. Especially, pattern-dependent global noise propagation and object jitter modelling methods for SPI are proposed. Subsequently, a deep-blind neural network is developed to remove the necessity of obtaining parameters of all the degradation factors in real-world image compensation. Our method can operate without degradation parameters and significantly improve the resolution and fidelity of SPI image reconstruction. The deep-blind network training is guided by the proposed comprehensive SPI degradation model that describes real-world SPI impairments, enabling the network to generalize across a wide range of degradation combinations. The experiment validates its advanced performance in real-world SPI imaging at ultra-low sampling rates. The proposed method holds great potential for applications in remote sensing, biomedical imaging, and privacy-preserving surveillance.

This paper presents a comprehensive and quantitative analysis of noise sources in real-world single-pixel imaging systems. Based on the proposed physical model, a robust and practical compensation network is developed.

Figures