Tetrolet regularization and learning for single frame image super-resolution

Authors:
Liang Xiao;Heng Li;Huixia Wang;Liqian Wang
Affiliations:
School of Computer Science, Nanjing University of Science and Technology, Nanjing, China;School of Computer Science, Nanjing University of Science and Technology, Nanjing, China;School of Computer Science, Nanjing University of Science and Technology, Nanjing, China;School of Computer Science, Nanjing University of Science and Technology, Nanjing, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 8
Cited 0

Single-frame image super-resolution through contourlet learning

EURASIP Journal on Applied Signal Processing
Split Bregman Algorithm, Douglas-Rachford Splitting and Frame Shrinkage

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Generalizing the Nonlocal-means to super-resolution reconstruction

IEEE Transactions on Image Processing
Super-resolution without explicit subpixel motion estimation

IEEE Transactions on Image Processing
A New Alternating Minimization Algorithm for Total Variation Image Reconstruction

SIAM Journal on Imaging Sciences
Tetrolet transform: A new adaptive Haar wavelet algorithm for sparse image representation

Journal of Visual Communication and Image Representation
Fast image recovery using variable splitting and constrained optimization

IEEE Transactions on Image Processing
Joint MAP registration and high-resolution image estimation using a sequence of undersampled images

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A single frame image super-resolution reconstruction technique is proposed with two stages contains tetrolet regularization and tetrolet learning. In the first stage, the tetrolet regularization is used to estimate an initial high-resolution image. In the second stage, the tetrolet coefficients at finer scales of the estimated high-resolution image are learned locally from a set of high-resolution training images. Finally the fusion of tetrolet reconstruction produces the super-resolution image. Experimental results demonstrated that the proposed method outperforms state-of-the-art super-resolution methods in terms of PSNR index and visual quality.