Title :
Multi-scale dictionary for single image super-resolution
Author :
Zhang, Kaibing ; Gao, Xinbo ; Tao, Dacheng ; Li, Xuelong
Author_Institution :
Sch. of E.E., Xidian Univ., Xi´´an, China
Abstract :
Reconstruction- and example-based super-resolution (SR) methods are promising for restoring a high-resolution (HR) image from low-resolution (LR) image(s). Under large magnification, reconstruction-based methods usually fail to hallucinate visual details while example-based methods sometimes introduce unexpected details. Given a generic LR image, to reconstruct a photo-realistic SR image and to suppress artifacts in the reconstructed SR image, we introduce a multi-scale dictionary to a novel SR method that simultaneously integrates local and non-local priors. The local prior suppresses artifacts by using steering kernel regression to predict the target pixel from a small local area. The non-local prior enriches visual details by taking a weighted average of a large neighborhood as an estimate of the target pixel. Essentially, these two priors are complementary to each other. Experimental results demonstrate that the proposed method can produce high quality SR recovery both quantitatively and perceptually.
Keywords :
image resolution; image restoration; regression analysis; HR image; SR method; SR recovery; example-based super-resolution; generic LR image; high-resolution image; image restoration; local prior; low-resolution image; multiscale dictionary; photorealistic SR image; reconstructed SR image; reconstruction method; single image super-resolution; steering kernel regression; weighted average; Dictionaries; Image edge detection; Image reconstruction; Kernel; Redundancy; Strontium; Training;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2012.6247791