Deep-learned orthogonal basis patterns for fast, noise-robust single-pixel imaging

TL;DR

This paper introduces a deep learning approach using a modified convolutional autoencoder to generate orthogonal basis patterns for single-pixel imaging, achieving fast, noise-robust reconstructions suitable for real-time applications.

Contribution

It presents a novel deep learning method that learns orthogonal basis patterns with regularizers, improving noise robustness and reconstruction speed in single-pixel imaging.

Findings

DCAN learns orthogonal, binary, and non-binary patterns.

Reconstruction time is approximately 3 ms per frame.

Models demonstrate robustness to noise compared to traditional algorithms.

Abstract

Single-pixel imaging (SPI) is a novel, unconventional method that goes beyond the notion of traditional cameras but can be computationally expensive and slow for real-time applications. Deep learning has been proposed as an alternative approach for solving the SPI reconstruction problem, but a detailed analysis of its performance and generated basis patterns when used for SPI is limited. We present a modified deep convolutional autoencoder network (DCAN) for SPI on 64x64 pixel images with up to 6.25% compression ratio and apply binary and orthogonality regularizers during training. Training a DCAN with these regularizers allows it to learn multiple measurement bases that have combinations of binary or non-binary, and orthogonal or non-orthogonal patterns. We compare the reconstruction quality, orthogonality of the patterns, and robustness to noise of the resulting DCAN models to traditional SPI reconstruction algorithms (such as Total Variation minimization and Fourier Transform). Our DCAN models can be trained to be robust to noise while still having fast enough reconstruction times (~3 ms per frame) to be viable for real-time imaging.