Benchmarking Super-Resolution Algorithms on Real Data

Weiterer Publikationstyp


Details zur Publikation

Autorinnen und Autoren: Köhler T, Bätz M, Naderi Boldaji F, Kaup A, Maier A, Riess C
Jahr der Veröffentlichung: 2017
Band: abs/1709.04881
Sprache: Englisch


Abstract

Over the past decades, various super-resolution (SR) techniques have been developed to enhance the spatial resolution of digital images. Despite the great number of methodical contributions, there is still a lack of comparative validations of SR under practical conditions, as capturing real ground truth data is a challenging task. Therefore, current studies are either evaluated 1) on simulated data or 2) on real data without a pixel-wise ground truth. 
To facilitate comprehensive studies, this paper introduces the publicly available Super-Resolution Erlangen (SupER) database that includes real low-resolution images along with high-resolution ground truth data. Our database comprises image sequences with more than 20k images captured from 14 scenes under various types of motions and photometric conditions. The datasets cover four spatial resolution levels using camera hardware binning. With this database, we benchmark 15 single-image and multi-frame SR algorithms. Our experiments quantitatively analyze SR accuracy and robustness under realistic conditions including independent object and camera motion or photometric variations.


FAU-Autorinnen und Autoren / FAU-Herausgeberinnen und Herausgeber

Bätz, Michel
Lehrstuhl für Multimediakommunikation und Signalverarbeitung
Kaup, André Prof. Dr.-Ing.
Lehrstuhl für Multimediakommunikation und Signalverarbeitung
Köhler, Thomas
Lehrstuhl für Informatik 5 (Mustererkennung)
Maier, Andreas Prof. Dr.-Ing.
Lehrstuhl für Informatik 5 (Mustererkennung)
Naderi Boldaji, Farzad
Lehrstuhl für Informatik 5 (Mustererkennung)
Rieß, Christian Dr.-Ing.
Lehrstuhl für Informatik 1 (IT-Sicherheitsinfrastrukturen)


Zitierweisen

APA:
Köhler, T., Bätz, M., Naderi Boldaji, F., Kaup, A., Maier, A., & Riess, C. (2017). Benchmarking Super-Resolution Algorithms on Real Data.

MLA:
Köhler, Thomas, et al. Benchmarking Super-Resolution Algorithms on Real Data. 2017.

BibTeX: 

Zuletzt aktualisiert 2019-11-04 um 17:08