Image Super-Resolution by TV-Regularization and Bregman Iteration

Authors:
Antonio Marquina;Stanley J. Osher
Affiliations:
Departamento de Matematica Aplicada, Universidad de Valencia, Burjassot, Spain 46100;Department of Mathematics, University of California Los Angeles, Los Angeles, USA 90095
Venue:
Journal of Scientific Computing
Year:
2008

Citing 9
Cited 15

Nonlinear total variation based noise removal algorithms

Proceedings of the eleventh annual international conference of the Center for Nonlinear Studies on Experimental mathematics : computational issues in nonlinear science: computational issues in nonlinear science
Super-Resolution Imaging

Super-Resolution Imaging
Explicit Algorithms for a New Time Dependent Model Based on Level Set Motion for Nonlinear Deblurring and Noise Removal

SIAM Journal on Scientific Computing
Edge Direction Preserving Image Zooming: A Mathematical and Numerical Analysis

SIAM Journal on Numerical Analysis
Total Variation Based Oversampling of Noisy Images

Scale-Space '01 Proceedings of the Third International Conference on Scale-Space and Morphology in Computer Vision
Inverse Scale Space Theory for Inverse Problems

Scale-Space '01 Proceedings of the Third International Conference on Scale-Space and Morphology in Computer Vision
Fast, robust total variation-based reconstruction of noisy, blurred images

IEEE Transactions on Image Processing
A local spectral inversion of a linearized TV model for denoising and deblurring

IEEE Transactions on Image Processing
Enlargement or reduction of digital images with minimum loss of information

IEEE Transactions on Image Processing

Edge-Enhanced Image Reconstruction Using (TV) Total Variation and Bregman Refinement

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Video Super Resolution Using Duality Based TV-L1 Optical Flow

Proceedings of the 31st DAGM Symposium on Pattern Recognition
MRI resolution enhancement using total variation regularization

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Image Recovery via Nonlocal Operators

Journal of Scientific Computing
Multiframe image restoration in the presence of noisy blur kernel

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Variational method for super-resolution optical flow

Signal Processing
Surface Reconstruction and Image Enhancement via $L^1$-Minimization

SIAM Journal on Scientific Computing
Subvoxel super-resolution of volumetric motion field using general order prior

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
A Fast Algorithm for Euler's Elastica Model Using Augmented Lagrangian Method

SIAM Journal on Imaging Sciences
Image reconstruction with locally adaptive sparsity and nonlocal robust regularization

Image Communication
Variational multiframe restoration of images degraded by noisy (stochastic) blur kernels

Journal of Computational and Applied Mathematics
Fractional order total variation regularization for image super-resolution

Signal Processing
Adaptive regularization-based space-time super-resolution reconstruction

Image Communication
Coupling Image Restoration and Segmentation: A Generalized Linear Model/Bregman Perspective

International Journal of Computer Vision
Total Cyclic Variation and Generalizations

Journal of Mathematical Imaging and Vision

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we formulate a new time dependent convolutional model for super-resolution based on a constrained variational model that uses the total variation of the signal as a regularizing functional. We propose an iterative refinement procedure based on Bregman iteration to improve spatial resolution. The model uses a dataset of low resolution images and incorporates a downsampling operator to relate the high resolution scale to the low resolution one. We present an algorithm for the model and we perform a series of numerical experiments to show evidence of the good behavior of the numerical scheme and quality of the results.