Compressive single-pixel imaging via a wavelength-multiplexed spatially incoherent diffractive optical processor

TL;DR

This paper introduces a novel wavelength-multiplexed diffractive optical processor combined with a neural network to significantly improve the efficiency and speed of single-pixel imaging, enabling rapid image reconstruction across broad spectral ranges.

Contribution

It presents a new optical and computational framework that jointly optimizes a static diffractive processor and a neural network for efficient compressive single-pixel imaging.

Findings

Achieved rapid image reconstruction using spectral encoding and neural decoding.

Validated the approach experimentally with LED arrays.

Demonstrated potential for biomedical, autonomous, and remote sensing applications.

Abstract

Despite offering high sensitivity, a high signal-to-noise ratio, and a broad spectral range, single-pixel imaging (SPI) is limited by low measurement efficiency and long data-acquisition times. To address this, we propose a wavelength-multiplexed, spatially incoherent diffractive optical processor combined with a compact/shallow digital artificial neural network (ANN) to implement compressive SPI. Specifically, we model the bucket detection process in conventional SPI as a linear intensity transformation with spatially and spectrally varying point-spread functions. This transformation matrix is treated as a learnable parameter and jointly optimized with a shallow digital ANN composed of 2 hidden nonlinear layers. The wavelength-multiplexed diffractive processor is then configured via data-free optimization to approximate this pre-trained transformation matrix; after this optimization, the diffractive processor remains static/fixed. Upon multi-wavelength illumination and diffractive modulation, the target spatial information of the input object is spectrally encoded. A single-pixel detector captures the output spectral power at each illumination band, which is then rapidly decoded by the jointly trained digital ANN to reconstruct the input image. In addition to our numerical analyses demonstrating the feasibility of this approach, we experimentally validated its proof-of-concept using an array of light-emitting diodes (LEDs). Overall, this work demonstrates a computational imaging framework for compressive SPI that can be useful in applications such as biomedical imaging, autonomous devices, and remote sensing.