A noise-suppressing and edge-preserving multiframe super-resolution image reconstruction method

Maiseli, Baraka; Ally, Nassor; Gao, Huijun

doi:10.1016/j.image.2015.03.001

Cited by 32 publications

(18 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, super-resolution methods based on a variety of regularizers, namely NC00 [20], TV [9], ANDIFF [21], and Hybrid, were applied on the degraded images to restore their original versions. Lastly, the objective metric, namely feature similarity (FSIM) [22], and the subjective metric were used to compare performances of different methods.…”

Section: Experimental Methodologymentioning

confidence: 99%

Diffusion-Steered Super-Resolution Image Reconstruction

Maiseli¹

2018

Colorimetry and Image Processing

View full text Add to dashboard Cite

For decades, super-resolution has been a widely applied technique to improve the spatial resolution of an image without hardware modification. Despite the advantages, super-resolution suffers from ill-posedness, a problem that makes the technique susceptible to multiple solutions. Therefore, scholars have proposed regularization approaches as attempts to address the challenge. The present work introduces a parameterized diffusion-steered regularization framework that integrates total variation (TV) and Perona-Malik (PM) smoothing functionals into the classical super-resolution model. The goal is to establish an automatic interplay between TV and PM regularizers such that only their critical useful properties are extracted to well pose the super-resolution problem, and hence, to generate reliable and appreciable results. Extensive analysis of the proposed resolution-enhancement model shows that it can respond well on different image regions. Experimental results provide further evidence that the proposed model outperforms.

show abstract

Section: Experimental Methodologymentioning

confidence: 99%

Diffusion-Steered Super-Resolution Image Reconstruction

Maiseli¹

2018

Colorimetry and Image Processing

View full text Add to dashboard Cite

show abstract

“…The resolution of this equation is related to the gradient descent optimization method. Recently, Maiseli et al propose in [38] the resolution of the evolution equation associated to the Euler-Lagrange form defined as…”

Section: 1mentioning

confidence: 99%

“…Lately, the Euler-Lagrange equation associated to an adaptive diffusion-based regularizer was treated to preserve edges [38]. Even if this approach preserves image features, it suffers from the blurring effect.…”

mentioning

confidence: 99%

A nonlinear fourth-order PDE for multi-frame image super-resolution enhancement

Laghrib¹,

Chakib²,

Hadri³

et al. 2020

Discrete &Amp; Continuous Dynamical Systems - B

View full text Add to dashboard Cite

The multiframe super-resolution (SR) techniques are considered as one of the active research fields. More precisely, the construction of the desired high resolution (HR) image with less artifacts in the SR models, which are always ill-posed problems, requires a great care. In this paper, we propose a new fourth-order equation based on a diffusive tensor that takes the benefit from the diffusion model of Perona-Malik in the flat regions and the Weickert model near boundaries with a high diffusion order. As a result, the proposed SR approach can efficiently preserve image features such as corner and texture much better with less blur near edges. The existence and uniqueness of the proposed partial differential equation (PDE) are also demonstrated in an appropriate functional space. Finally, the given experimental results show the effectiveness of the proposed PDE compared to some competitive methods in both visually and quantitatively.

show abstract

“…The main principle of these approaches is to provide a global minimum to the encountered minimization problem. With the same aim, recently, Maiseli et al [37] proposed a new regularizing potential defined by…”

Section: Muti-frame Sr Problem Formulationmentioning

confidence: 99%

“…In the same principle, another adaptive combined of the TV and BTV norms was introduced to avoid the straicasing effect, which increase the performance of the restoration step of the SR algorithm [36]. Recently, an adaptive diffusion-based regularizer was treated to preserve important image features [37]. Even if this approach avoids undesirable artifacts while suppressing noise, it suffers from the blurring effect.…”

Section: Introductionmentioning

confidence: 99%

A new denoising model for multi-frame super-resolution image reconstruction

et al. 2017

View full text Add to dashboard Cite

Multi-frame image super-resolution (SR) aims to combine the sub-pixel information from a sequence of low-resolution (LR) images to build a highresolution (HR) one. SR techniques usually suffers from annoying restoration artifacts such as noise, jagged edges, and staircasing effect. In this paper, we aim to increase the performance of SR reconstitution under a variational framework using adaptive diffusion-based regularization term. We propose a new tensor based diffusion regularization that takes the benefit from the diffusion model of Perona-Malik in the flat regions and use a nonlinear tensor derived from the diffusion process of weickert filter near boundaries. Thus, the proposed SR approach can preserve important image features (sharp edges and corners) much better while avoiding artifacts. The synthetic and real experimental results show the effectiveness of the proposed regularisation compared to other methods in both quantitatively and visually.

show abstract

A noise-suppressing and edge-preserving multiframe super-resolution image reconstruction method

Cited by 32 publications

References 44 publications

Diffusion-Steered Super-Resolution Image Reconstruction

Diffusion-Steered Super-Resolution Image Reconstruction

A nonlinear fourth-order PDE for multi-frame image super-resolution enhancement

A new denoising model for multi-frame super-resolution image reconstruction

Contact Info

Product

Resources

About