Superresolution reconstruction using nonlinear gradient-based regularization

Authors:
Xin Zhang;Edmund Y. Lam
Affiliations:
Department of Electrical and Electronic Engineering, The University of Hong Kong, Kowloon, Hong Kong;Department of Electrical and Electronic Engineering, The University of Hong Kong, Kowloon, Hong Kong
Venue:
Multidimensional Systems and Signal Processing
Year:
2009

Citing 7
Cited 2

Choosing Regularization Parameters in Iterative Methods for Ill-Posed Problems

SIAM Journal on Matrix Analysis and Applications
Self-Adaptive Regularization

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Gradient Based Weighted Averaging Method for Estimation of Fingerprint Orientation Fields

DICTA '05 Proceedings of the Digital Image Computing on Techniques and Applications
Super-resolution reconstruction in a computational compound-eye imaging system

Multidimensional Systems and Signal Processing
Deterministic edge-preserving regularization in computed imaging

IEEE Transactions on Image Processing
Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images

IEEE Transactions on Image Processing
Nonlinear image recovery with half-quadratic regularization

IEEE Transactions on Image Processing

Source localization using a sparse representation framework to achieve superresolution

Multidimensional Systems and Signal Processing
A robust multiframe super-resolution algorithm based on half-quadratic estimation with modified BTV regularization

Digital Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses the problem of superresolution reconstruction. To preserve edges accurately and efficiently in the reconstruction, we propose a nonlinear gradient-based regularization that uses the gradient vector field of a preliminary high resolution image to configure a regularization matrix and compute the regularization parameters. Compared with other existing methods, it not only enhances the spatial resolution of the resulting images, but can also preserve edges and smooth noise to a greater extent. The advantages are shown in simulations and experiments with synthetic and real images.