Saved in:
Bibliographic Details
Main Authors: Shi, Jing-yi, Song, Jia-qi, Ji, Peng-cheng, Zhao, Zi-qing, Yu, Yuan-jin, Li, Ming-fei, Wu, Ling-an
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.22088
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915640442355712
author Shi, Jing-yi
Song, Jia-qi
Ji, Peng-cheng
Zhao, Zi-qing
Yu, Yuan-jin
Li, Ming-fei
Wu, Ling-an
author_facet Shi, Jing-yi
Song, Jia-qi
Ji, Peng-cheng
Zhao, Zi-qing
Yu, Yuan-jin
Li, Ming-fei
Wu, Ling-an
contents Single-pixel imaging(SPI),especially when integrated with deep neural networks like deep image prior networks (DIP-Net) or data-driven networks (DD-Net), has gained considerable attention for its capability to generate high-quality reconstructed images, even in the presence of sub-sampling conditions. However, DIP-Net often requires thousands of iterations to achieve high-quality image reconstruction, and DD-Net performs optimally only when the target closely resembles the features present in its training set. To overcome these limitations, we propose a dual-network iterative optimization (SPI-DNIO) framework that combines the strengths of both DD-Net and DIP-Net. It has been demonstrated that this approach can recover high-quality images with fewer iteration steps. Furthermore, to address the challenge of SPI inputs having less effective information at low sampling rates, we have designed a residual block enriched with gradient information, which can convey details to deeper layers, thereby enhancing the deep network's learning capabilities. We have applied these techniques to both indoor experiments with active lighting and outdoor long-range experiments with passive lighting. Our experimental results confirm the exceptional reconstruction capabilities and generalization performance of the SPI-DNIO framework.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22088
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Single-pixel imaging via data-driven and deep image prior dual networks
Shi, Jing-yi
Song, Jia-qi
Ji, Peng-cheng
Zhao, Zi-qing
Yu, Yuan-jin
Li, Ming-fei
Wu, Ling-an
Computational Physics
Optics
Single-pixel imaging(SPI),especially when integrated with deep neural networks like deep image prior networks (DIP-Net) or data-driven networks (DD-Net), has gained considerable attention for its capability to generate high-quality reconstructed images, even in the presence of sub-sampling conditions. However, DIP-Net often requires thousands of iterations to achieve high-quality image reconstruction, and DD-Net performs optimally only when the target closely resembles the features present in its training set. To overcome these limitations, we propose a dual-network iterative optimization (SPI-DNIO) framework that combines the strengths of both DD-Net and DIP-Net. It has been demonstrated that this approach can recover high-quality images with fewer iteration steps. Furthermore, to address the challenge of SPI inputs having less effective information at low sampling rates, we have designed a residual block enriched with gradient information, which can convey details to deeper layers, thereby enhancing the deep network's learning capabilities. We have applied these techniques to both indoor experiments with active lighting and outdoor long-range experiments with passive lighting. Our experimental results confirm the exceptional reconstruction capabilities and generalization performance of the SPI-DNIO framework.
title Single-pixel imaging via data-driven and deep image prior dual networks
topic Computational Physics
Optics
url https://arxiv.org/abs/2511.22088