Fast and robust filtering-based image magnification

Authors:
Wenze Shao;Zhihui Wei
Affiliations:
Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China;Graduate School, Nanjing University of Science and Technology, Nanjing, China
Venue:
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Year:
2006

Citing 13
Cited 1

A Fundamental Relationship between Bilateral Filtering, Adaptive Smoothing, and the Nonlinear Diffusion Equation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Super-Resolution from Image Sequences - A Review

MWSCAS '98 Proceedings of the 1998 Midwest Symposium on Systems and Circuits
Bilateral Filtering for Gray and Color Images

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Efficient implementation of image interpolation as an inverse problem

Digital Signal Processing
Deterministic edge-preserving regularization in computed imaging

IEEE Transactions on Image Processing
Regularity-preserving image interpolation

IEEE Transactions on Image Processing
The digital TV filter and nonlinear denoising

IEEE Transactions on Image Processing
Least-squares image resizing using finite differences

IEEE Transactions on Image Processing
New edge-directed interpolation

IEEE Transactions on Image Processing
On the origin of the bilateral filter and ways to improve it

IEEE Transactions on Image Processing
Linear interpolation revitalized

IEEE Transactions on Image Processing
Fast and robust multiframe super resolution

IEEE Transactions on Image Processing
Specification of the observation model for regularized image up-sampling

IEEE Transactions on Image Processing

A fully automatic one-scan adaptive zooming algorithm for color images

Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image magnification, or interpolation, produces a high resolution image from a low resolution, and perhaps noisy image. There have been proposed a variety of magnification algorithms. However, they are either sensitive to the noise, or non-robust to the blocking artifacts, or of high computational complexity, which hence limits their utility. In this paper, we propose an alternative magnification approach utilizing a filtering-based implementation scheme and novel regularization through coupling bilateral filtering with the digital total variation model. The approach is simple, fast, and robust to both the noise and blocking artifacts. Experiment results demonstrate the effectiveness of our approach.