Paper Info
Title
Single image super-resolution using Gaussian Mixture Model
Abstract
In this paper we present a novel method for single image super-resolution (SR). Given an input low-resolution image, we create a pyramid pair: the ground truth pyramid and the interpolated pyramid. This method aims to model the relationship between pixel value in ground truth pyramid and its corresponding 8- neighborhood vector in interpolated pyramid using Gaussian Mixture Model (GMM). Each pixel in final high-resolution image is predicted by its corresponding 8- neighborhood vector through the trained GMM. Unlike the previous example-based SR method, our algorithm only utilizes the information of input image rather than the external image database. Our proposed algorithm achieves much better results than the state of the art algorithms in terms of both objective measurement and visual perception.
Year
Venue
Keywords
2012
ICPR
interpolated pyramid,single image super resolution,gmm,objective measurement,image resolution,visual databases,single image sr,ground truth pyramid,example-based sr method,pyramid pair,input low-resolution image,gaussian processes,external image database,visual perception,high-resolution image,8-neighborhood vector,gaussian mixture model
Field
DocType
ISSN
Computer vision,Pattern recognition,Feature detection (computer vision),Computer science,Pyramid (image processing),Ground truth,Pyramid,Pixel,Gaussian process,Artificial intelligence,Image resolution,Mixture model
Conference
1051-4651
ISBN
Citations 
PageRank 
978-1-4673-2216-4
0
0.34
References 
Authors
4
3
Name
Order
Citations
PageRank
Huayong He100.34
Jianhong Li200.34
Xiaonan Luo369792.76