Towards high-resolution undersampled single-pixel imaging: A neural network perspective

Saad Rizvi*, Jie Cao*, Qun Hao, Yang Cheng

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a novel single-pixel imaging (SPI) framework which can produce high-resolution target images with undersampling. Undersampling is used to work around the problem of long imaging time in SPI for real-time applications. However, the reconstruction from undersampled measurements suffers from noise, ringing or pixelated artifacts, and low resolution which complicates target recognition. To improve image quality, deep learning (DL) based approaches have been proposed but the improvement is merely based on noise and artifact removal. In order to improve image resolution, it is necessary to recover fine details from undersampled input which is very challenging due to absence of high-frequency information (during target reconstruction). To achieve this task, we propose to apply a DL model which learns to generate both low and high-frequency representations from an undersampled (10%) 96*96 input, and combines them to produce a high-quality (high-resolution) output. Experimental results show that the proposed model is robust against noise and frequency-based artifacts, and reconstructs high-quality targets by improving resolution (fine details).

Original languageEnglish
Title of host publicationAOPC 2020
Subtitle of host publicationOptical Sensing and Imaging Technology
EditorsXiangang Luo, Yadong Jiang, Jin Lu, Dong Liu
PublisherSPIE
ISBN (Electronic)9781510639553
DOIs
Publication statusPublished - 2020
Event2020 Applied Optics and Photonics China: Optical Sensing and Imaging Technology, AOPC 2020 - Xiamen, China
Duration: 25 Aug 202027 Aug 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11567
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2020 Applied Optics and Photonics China: Optical Sensing and Imaging Technology, AOPC 2020
Country/TerritoryChina
CityXiamen
Period25/08/2027/08/20

Keywords

  • Single-pixel imaging
  • deep learning
  • denoising
  • deringing
  • high-resolution imaging
  • real-time imaging

Fingerprint

Dive into the research topics of 'Towards high-resolution undersampled single-pixel imaging: A neural network perspective'. Together they form a unique fingerprint.

Cite this