Example-based image super-resolution with class-specific predictors

Authors:
Xiaoguang Li;Kin Man Lam;Guoping Qiu;Lansun Shen;Suyu Wang
Affiliations:
Signal and Information Processing Laboratory, Beijing University of Technology, Beijing 100124, China and Centre for Signal Processing, Department of Electronic and Information Engineering, The Ho ...;Centre for Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong;School of Computer Science, University of Nottingham, UK;Signal and Information Processing Laboratory, Beijing University of Technology, Beijing 100124, China;Signal and Information Processing Laboratory, Beijing University of Technology, Beijing 100124, China
Venue:
Journal of Visual Communication and Image Representation
Year:
2009

Citing 13
Cited 7

Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Example-Based Super-Resolution

IEEE Computer Graphics and Applications
Limits on Super-Resolution and How to Break Them

IEEE Transactions on Pattern Analysis and Machine Intelligence
Patch Based Blind Image Super Resolution

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Adaptive Markov random fields for example-based super-resolution of faces

EURASIP Journal on Applied Signal Processing
Image magnification based on a blockwise adaptive Markov random field model

Image and Vision Computing
Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image

The Computer Journal
A progressively predictive image pyramid for efficient lossless coding

IEEE Transactions on Image Processing
Fast and robust multiframe super resolution

IEEE Transactions on Image Processing
Image up-sampling using total-variation regularization with a new observation model

IEEE Transactions on Image Processing
An image super-resolution algorithm for different error levels per frame

IEEE Transactions on Image Processing
Super-Resolution Based on Fast Registration and Maximum a Posteriori Reconstruction

IEEE Transactions on Image Processing
Solving the inverse problem of image zooming using "self-examples"

ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition

Wavelet-based eigentransformation for face super-resolution

PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
A novel kernel-based framework for facial-image hallucination

Image and Vision Computing
Eigentransformation-based face super-resolution in the wavelet domain

Pattern Recognition Letters
Human face super-resolution based on NSCT

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Classification-based video super-resolution using artificial neural networks

Signal Processing
Face hallucination based on sparse local-pixel structure

Pattern Recognition
Single-image super-resolution reconstruction based on global non-zero gradient penalty and non-local Laplacian sparse coding

Digital Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Example-based super-resolution is a promising approach to solving the image super-resolution problem. However, the learning process can be slow and prediction can be inaccurate. In this paper, we present a novel learning-based algorithm for image super-resolution to improve the computational speed and prediction accuracy. Our new method classifies image patches into several classes, for each class, a class-specific predictor is designed. A class-specific predictor takes a low-resolution image patch as input and predicts a corresponding high-resolution patch as output. The performances of the class-specific predictors are evaluated using different datasets formed by face images and natural-scene images. We present experimental results which demonstrate that the new method provides improved performances over existing methods.