Share Email Print
cover

Proceedings Paper

Deep learning for fast super-resolution reconstruction from multiple images
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Recent advancements in single-image super-resolution reconstruction (SRR) are attributed primarily to convolutional neural networks (CNNs), which effectively learn the relation between low and high resolution and allow for obtaining high-quality reconstruction within seconds. SRR from multiple images benefits from information fusion, which improves the reconstruction outcome compared with example-based methods. On the other hand, multiple-image SRR is computationally more demanding, mainly due to required subpixel registration of the input images. Here, we explore how to exploit CNNs in multiple-image SRR and we demonstrate that competitive reconstruction outcome can be obtained within seconds.

Paper Details

Date Published: 14 May 2019
PDF: 8 pages
Proc. SPIE 10996, Real-Time Image Processing and Deep Learning 2019, 109960B (14 May 2019); doi: 10.1117/12.2519579
Show Author Affiliations
Michal Kawulok, Silesian Univ. of Technology (Poland)
Future Processing (Poland)
Pawel Benecki, Silesian Univ. of Technology (Poland)
Future Processing (Poland)
Krzysztof Hrynczenko, Silesian Univ. of Technology (Poland)
Future Processing (Poland)
Daniel Kostrzewa, Silesian Univ. of Technology (Poland)
Future Processing (Poland)
Szymon Piechaczek, Silesian Univ. of Technology (Poland)
Future Processing (Poland)
Jakub Nalepa, Silesian Univ. of Technology (Poland)
Future Processing (Poland)
Bogdan Smolka, Silesian Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 10996:
Real-Time Image Processing and Deep Learning 2019
Nasser Kehtarnavaz; Matthias F. Carlsohn, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray