2 Iterative back propagation Super resolution (original) (raw)

A robust combination interpolation method for video super-resolution

Science and Technology Development Journal, 2013

This paper presents an efficient method for video super-resolution (SR) based on two main ideals: Firstly, input video frames can be separated into two components, nontexturing image and texturing image. Then each component image is applied to a compatible interpolation method to improve the quality of high-resolution (HR) reconstructed frame. Secondly, based on the approach that border regions of image details are the most lossy information regions from the sampling process. Therefore, a task of compensation interpolation is essential to increase the quality of the reconstructed HR images. From these discussions, we proposed an efficient method for video SR by combining the spatial interpolation in different texturing regions and the sampling compensation interpolation to improve the quality of video super-resolution. Our results shown that, the quality of HR frames, reconstructed by the proposed method, is better than that of other methods, , and in recently. The significant contr...

Video Super-Resolution by Motion Compensated Iterative Back-Projection Approach

Journal of information …, 2011

Traditionally, uniform interpolation based approach is adopted to enhance the image resolution from a single image. Due to the one and only one image, the quality of the reconstructed image is thus constrained. Multiple frames as additional information are utilized to do super-resolution for higher-resolution image. If we have enough low-resolution images with observed sub-pixels, the high-resolution image can be reconstructed. To deal with general cases, we adopted non-uniform interpolation by iterative back-projection to estimate the high resolution image. Motion compensation is used to accurately back-project the kernel and make the process converge efficiently. Motion masks are produced for useful images/regions selection and sub-pixel blocks matching are used to do motion estimation. Objects are assumed to move slightly between two consecutive images. Thus, erroneous motion vectors could be corrected by the center of motion vector clusters. From experimental results, the PSNRs of proposed method were higher than the others, ranging from 0.5 to 1.6 dB. The difference values of the high frequency parts were also greater from 0.63% to 4.86%. It demonstrated the feasibility of the proposed method.

Motion-Based Localized Super Resolution Technique for Low Resolution Video Enhancement

2008

ABSTRACT Super resolution (SR) can be used for enhancing the resolution of images or video sequences. However, because of the computational complexity, SR is not an efficient way to improve the quality of a given video sequence. In order to overcome this problem we proposed a method, where we super resolve consecutive frames in a given video sequence in such a way that only the moving regions in the frames instead of the whole frames are processed, saving the computational cost.

Image Interpolation by Super-Resolution

Term "super-resolution" is typically used for a high-resolution image produced from several low-resolution noisy observations. In this paper, we consider the problem of high-quality interpolation of a single noise-free image. Several aspects of the corresponding super-resolution algorithm are investigated: choice of regularization term, dependence of the result on initial approximation, convergence speed, and heuristics to facilitate convergence and improve the visual quality of the resulting image.

A multi-frame image super-resolution method

Signal Processing, 2010

Multi-frame image super-resolution (SR) aims to utilize information from a set of lowresolution (LR) images to compose a high-resolution (HR) one. As it is desirable or essential in many real applications, recent years have witnessed the growing interest in the problem of multi-frame SR reconstruction. This set of algorithms commonly utilizes a linear observation model to construct the relationship between the recorded LR images to the unknown reconstructed HR image estimates. Recently, regularizationbased schemes have been demonstrated to be effective because SR reconstruction is actually an ill-posed problem. Working within this promising framework, this paper first proposes two new regularization items, termed as locally adaptive bilateral total variation and consistency of gradients, to keep edges and flat regions, which are implicitly described in LR images, sharp and smooth, respectively. Thereafter, the combination of the proposed regularization items is superior to existing regularization items because it considers both edges and flat regions while existing ones consider only edges. Thorough experimental results show the effectiveness of the new algorithm for SR reconstruction.

Fast and robust super-resolution

Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429), 2003

In the last two decades, many papers have been published, proposing a variety methods of multi-frame resolution enhancement. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. We propose a different implementation using L 1 norm minimization and robust regularization to deal with different data and noise models. This computationally inexpensive method is robust to errors in motion and blur estimation, and results in sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other robust super-resolution methods.

Motion Compensated Video Super Resolution

Lecture Notes in Computer Science, 2007

In this paper we present a variational, spatiotemporal video super resolution scheme that produces not just one but n high resolution video frames from an n frame low resolution video sequence. We use a generic prior and the output is artifact-free, sharp and superior in quality to state of the art home cinema video processors. Unlike many other super resolution schemes, ours does not limit itself to just translational or affine motion, or to certain subclasses of image content to optimize the output quality. We present a link between image reconstruction and super resolution and formulate our super resolution constraint with arbitrary up-scaling factors in space from that.

A multi-frame super-resolution method based on the variable-exponent nonlinear diffusion regularizer

EURASIP Journal on Image and Video Processing, 2015

In this work, the authors have proposed a multi-frame super-resolution method that is based on the diffusion-driven regularization functional. The new regularizer contains a variable exponent that adaptively regulates its diffusion mechanism depending upon the local image features. In smooth regions, the method favors linear isotropic diffusion, which removes noise more effectively and avoids unwanted artifacts (blocking and staircasing). Near edges and contours, diffusion adaptively and significantly diminishes, and since noise is hardly visible in these regions, an image becomes sharper and resolute-with noise being largely reduced in flat regions. Empirical results from both simulated and real experiments demonstrate that our method outperforms some of the state-of-the-art classical methods based on the total variation framework.

An image super-resolution algorithm for different error levels per frame

IEEE Transactions on Image Processing, 2006

In this paper, we propose an image super-resolution (resolution enhancement) algorithm that takes into account inaccurate estimates of the registration parameters and the point spread function. These inaccurate estimates, along with the additive Gaussian noise in the low-resolution (LR) image sequence, result in different noise level for each frame. In the proposed algorithm, the LR frames are adaptively weighted according to their reliability and the regularization parameter is simultaneously estimated. A translational motion model is assumed. The convergence property of the proposed algorithm is analyzed in detail. Our experimental results using both real and synthetic data show the effectiveness of the proposed algorithm.

Robust Shift and Add Approach to Super-Resolution

2003

In the last two decades, many papers have been published, proposing a variety of methods for multi-frame resolution enhancement. These methods, which have a wide range of complexity, memory and time requirements, are usually very sensitive to their assumed model of data and noise, often limiting their utility. Different implementations of the non-iterative Shift and Add concept have been proposed as very fast and effective superresolution algorithms. The paper of Elad & Hel-Or 2001 provided an adequate mathematical justification for the Shift and Add method for the simple case of an additive Gaussian noise model. In this paper we prove that additive Gaussian distribution is not a proper model for super-resolution noise. Specifically, we show that L p norm minimization (1 ≤ p ≤ 2) results in a pixelwise weighted mean algorithm which requires the least possible amount of computation time and memory and produces a maximum likelihood solution. We also justify the use of a robust prior information term based on bilateral filter idea. Finally, for the underdetermined case, where the number of non-redundant low-resolution frames are less than square of the resolution enhancement factor, we propose a method for detection and removal of outlier pixels. Our experiments using commercial digital cameras show that our proposed super-resolution method provides significant improvements in both accuracy and efficiency.