3D Super-resolution Optical Imaging Using Deep Image Prior

Ruoxin Wang, Chi Fai Cheung

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Deep learning based super-resolution methods have received much attention, especially unsupervised super-resolution due to the difficulty of collecting images pairs (low-resolution and high-resolution images from the same scenario) in many fields, such as optics. Optical imaging is typical technique in advance optical measurement equipment and optical super-resolution imaging has received much attention. In this paper, a novel model, deep image prior with design surface model (DIP-DSM), based on deep image prior to improve the resolution of optical imaging is presented. It makes use of single image instead of using random input in which the design surface model is regarded as prior information. To validate the model, a series of experiments are conducted, and the results show the superiority of the proposed model as compared with deep image prior. Furthermore, the performance of different neural networks are explored and it is find that the U-Net achieve best reconstruction quality and reach to PSNR, 32.937.

Original languageEnglish
Title of host publication2021 International Conference of Optical Imaging and Measurement, ICOIM 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5-8
Number of pages4
ISBN (Electronic)9780738112121
DOIs
Publication statusPublished - 27 Aug 2021
Event2021 International Conference of Optical Imaging and Measurement, ICOIM 2021 - Xi'an, China
Duration: 27 Aug 202129 Aug 2021

Publication series

Name2021 International Conference of Optical Imaging and Measurement, ICOIM 2021

Conference

Conference2021 International Conference of Optical Imaging and Measurement, ICOIM 2021
Country/TerritoryChina
CityXi'an
Period27/08/2129/08/21

Keywords

  • Deep image prior
  • deep learning
  • measurement
  • optical imaging
  • precision metrology
  • precision surface measurement
  • Super-resolutuon

ASJC Scopus subject areas

  • Signal Processing
  • Instrumentation
  • Atomic and Molecular Physics, and Optics

Fingerprint

Dive into the research topics of '3D Super-resolution Optical Imaging Using Deep Image Prior'. Together they form a unique fingerprint.

Cite this