Deep learning-based video stream reconstruction in mass-production diffractive optical systems
Authors:
- Samara National Research UniversitySUSamara National Research University
- V. EvdokimovaVEV. Evdokimova
- M. PetrovMPM. Petrov
- M. KlyuevaMKM. Klyueva
- Ipsi Ras - Branch Of The Fsrc “Crystallography And Photonics” RasIRIpsi Ras - Branch Of The Fsrc “Crystallography And Photonics” Ras
- E. ZybinEZE. Zybin
- Federal State Unitary Enterprise State Research Institute of Aviation SystemsFSFederal State Unitary Enterprise State Research Institute of Aviation Systems
- V. KosianchukVKV. Kosianchuk
- I. MishchenkoIMI. Mishchenko
- V. NovikovVNV. Novikov
- N. SelvesiukNSN. Selvesiuk
- E. ErshovEEE. Ershov
- 1 February 2021
- journal article
- research article
- Published by Samara National Research University in Computer Optics
- Vol. 45 (1) , 130-+
Abstract
Many recent studies have focused on developing image reconstruction algorithms in optical systems based on flat optics. These studies demonstrate the feasibility of applying a combination of flat optics and the reconstruction algorithms in real vision systems. However, additional causes of quality loss have been encountered in the development of such systems. This study investigates the influence on the reconstructed image quality of such factors as limitations of mass production technology for diffractive optics, lossy video stream compression artifacts, and specificities of a neural network approach to image reconstruction. The paper offers an end-to-end deep learning-based image reconstruction framework to compensate for the additional factors of quality losing. It provides the image reconstruction quality sufficient for applied vision systems.Keywords
Funding Information
- Russian Science Foundation (20-69-47110)
- Russian Foundation for Basic Research (18-07-01390-А)
- Ministry of Science and Higher Education of the Russian Federation (007-ГЗ/Ч3363/2б)
This publication has 24 references indexed in Scilit:
- Loss Functions for Image Restoration With Neural NetworksIEEE Transactions on Computational Imaging, 2016
- Computational imaging using lightweight diffractive-refractive opticsOptics Express, 2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fresnel lens imaging with post-capture image processing2015
- Quality of experience evaluation of H.265/MPEG-HEVC and VP9 comparison efficiency2014
- Introduction2013
- Multiscale structural similarity for image quality assessment2004
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Harmonic diffractive lensesApplied Optics, 1995
- Robust Estimation of a Location ParameterThe Annals of Mathematical Statistics, 1964