Deep learning-based video stream reconstruction in mass-production diffractive optical systems
| Autor: | E. Ershov, M. Klyueva, N. A. Ivliev, Maksim Petrov, I. Mishchenko, V. Kosianchuk, N. Selvesiuk, Nikolay L. Kazanskiy, E. Zybin, V. Novikov, Artem V. Nikonorov, Roman V. Skidanov, V. Evdokimova |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
diffractive lenses
diffractive optics deep learning-based reconstruction Computer science business.industry Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology 01 natural sciences lcsh:Q350-390 Atomic and Molecular Physics and Optics Computer Science Applications image processing 010309 optics Computer graphics (images) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering lcsh:Information theory Production (economics) lcsh:QC350-467 Artificial intelligence Electrical and Electronic Engineering business lcsh:Optics. Light |
| Zdroj: | Компьютерная оптика, Vol 45, Iss 1, Pp 130-141 (2021) |
| ISSN: | 2412-6179 0134-2452 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|