Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding

Abstract : 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.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-00747054
Contributor : Marco Bevilacqua <>
Submitted on : Thursday, November 15, 2012 - 9:34:12 PM
Last modification on : Thursday, November 15, 2018 - 11:57:53 AM
Long-term archiving on : Saturday, December 17, 2016 - 6:21:55 AM

File

bmvc_final_submitted.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00747054, version 1

Citation

Marco Bevilacqua, Aline Roumy, Christine Guillemot, Marie-Line Alberi Morel. Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding. British Machine Vision Conference (BMVC), Sep 2012, Guildford, Surrey, United Kingdom. ⟨hal-00747054⟩

Share

Metrics

Record views

10299

Files downloads

330