Paper Info
Title
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.
Year
DOI
Venue
2012
10.5244/C.26.135
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2012
Field
DocType
Citations 
k-nearest neighbors algorithm,Feature vector,Embedding,Pattern recognition,Computer science,Competitive algorithm,Artificial intelligence,Superresolution,Computation
Conference
268
PageRank 
References 
Authors
9.57
10
4
Search Limit
100268
Name
Order
Citations
PageRank
Marco Bevilacqua131012.14
Aline Roumy246432.54
Christine Guillemot31286104.25
Marie-Line Alberi-Morel435120.31