DocumentCode :
3205642
Title :
Super-resolution through neighbor embedding
Author :
Hong Chang ; Dit-Yan Yeung ; Yimin Xiong
Author_Institution :
Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., Kowloon, China
Volume :
1
fYear :
2004
fDate :
June 27 2004-July 2 2004
Abstract :
In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its high-resolution counterpart using a set of training examples. While this formulation resembles other learning-based methods for super-resolution, our method has been inspired by recent manifold teaming methods, particularly locally linear embedding (LLE). Specifically, small image patches in the lowand high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector corresponding to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness constraints between patches in the target high-resolution image through overlapping. Experiments show that our method is very flexible and gives good empirical results.
Keywords :
computational geometry; feature extraction; filtering theory; gradient methods; image representation; image resolution; interpolation; learning (artificial intelligence); minimisation; splines (mathematics); feature vector spaces; filtering theory; gradient methods; high resolution counterpart; high resolution embedding estimation; image patches; image representation; interpolation; learning based methods; local geometry; locally linear embedding method; low resolution image; minimisation; single image super-resolution; splines; training image pairs; training set; Application software; Geometry; Image generation; Image resolution; Interpolation; Layout; Learning systems; Smoothing methods; Spatial resolution; Web pages;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on
Conference_Location :
Washington, DC, USA
ISSN :
1063-6919
Print_ISBN :
0-7695-2158-4
Type :
conf
DOI :
10.1109/CVPR.2004.1315043
Filename :
1315043
Link To Document :
بازگشت