Logo eprints

Low-complexity single-image super-resolution based on nonnegative neighbor embedding

Bevilacqua, Marco and Roumy, Aline and Guillemot, Christine and Alberi-Morel, Marie Line Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the 23rd British Machine Vision Conference (BMVC). BMVA Press, 135.1-135.10. ISBN 1-901725-46-4 (2012)

PDF - Published Version
Download (1MB) | Preview


This paper describes a single-image super-resolution (SR) algorithm based on nonnegative neighbor embedding. It belongs to the family of single-image example-based SR algorithms, since it uses a dictionary of low resolution (LR) and high resolution (HR) trained patch pairs to infer the unknown HR details. Each LR feature vector in the input image is expressed as the weighted combination of its K nearest neighbors in the dictionary; the corresponding HR feature vector is reconstructed under the assumption that the local LR embedding is preserved. Three key aspects are introduced in order to build a low-complexity competitive algorithm: (i) a compact but efficient representation of the patches (feature representation) (ii) an accurate estimation of the patches by their nearest neighbors (weight computation) (iii) a compact and already built (therefore external) dictionary, which allows a one-step upscaling. The neighbor embedding SR algorithm so designed is shown to give good visual results, comparable to other state-of-the-art methods, while presenting an appreciable reduction of the computational time.

Item Type: Book Section
Identification Number: 10.5244/C.26.135
Additional Information: British Machine Vision Conference, Surrey, UK, 3-7 September 2012
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Research Area: Computer Science and Applications
Depositing User: Ms T. Iannizzi
Date Deposited: 11 Dec 2014 11:00
Last Modified: 16 Dec 2014 14:34
URI: http://eprints.imtlucca.it/id/eprint/2412

Actions (login required)

Edit Item Edit Item