Texture-Aware Deblurring for Remote Sensing Images Using $ \ell _0$-Based Deblurring and $ \ell _2$-Based Fusion

Lim, Heunseung; Yu, Shuhui; Park, Kwanwoo; Seo, Doochun; Paik, Joonki

doi:10.1109/jstars.2020.2999961

Cited by 16 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, W denotes the Gaussian noise added to the original image. One approach is to use the plug-andplay framework, which involves applying the trained denoiser within the proposed update rules described in (14) and iterating until convergence is achieved. However, as the neural network optimization is independent of the blurring kernel and the blurred data, the HQS solver requires a significant number of iterations to converge and produce desirable results.…”

Section: Proposed Hqs Solvermentioning

confidence: 99%

“…Taking into account the drawbacks of the plug-and-play methodology, our aim is to develop a deep unrolling hyperspectral deconvolution network based on the proposed well-justified optimization solver (14). To accomplish this, a small number of iterations of the HQS solver (14), for instance, K = 5 − 10, are unrolled to establish a highly interpretable network. Each iteration of the proposed solver corresponds to a distinct layer within this K-layer unrolling architecture.…”

Section: A Proposed Deep Unrolling Networkmentioning

confidence: 99%

“…In [12], the spatialspectral joint total variation is employed to model the 3D structure of hyperspectral images. From a spectral perspective, the works in [13], [14] introduce the dark channel prior for HSI deblurring, along with the l0and l1-based Total Variation (TV) regularizers. In study [15], both spatial non-local selfsimilarity and spectral correlations investigated using lowrank tensor priors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising

Gkillas

Ampeliotis

Berberidis

2023

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we propose a novel methodology for addressing the hyperspectral image deconvolution problem. This problem is highly ill-posed, and thus, requires proper priors (regularizers) to model the inherent spectral-spatial correlations of the HSI signals. To this end, a new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. To tackle this problem, an effective solver is proposed using the half quadratic splitting methodology. The derived iterative solver is then expressed as a fixedpoint calculation problem within the Deep Equilibrium (DEQ) framework, resulting in an interpretable architecture, with clear explainability to its parameters and convergence properties with practical benefits. The proposed model is a first attempt to handle the classical HSI degradation problem with different blurring kernels and noise levels via a single deep equilibrium model with significant computational efficiency. Extensive numerical experiments validate the superiority of the proposed methodology over other state-of-the-art methods. This superior restoration performance is achieved while requiring 99.85% less computation time as compared to existing methods.

show abstract

Section: Proposed Hqs Solvermentioning

confidence: 99%

Section: A Proposed Deep Unrolling Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising

Gkillas

Ampeliotis

Berberidis

2023

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Further, Henrot et al [150] introduced the Huber-Markov variational model with spatially local adaptive edge-preserving ability for HSIs deblurring. From the spectral viewpoint, Cao et al [151] and Lim et al [152] presented the dark channel prior for HSIs deblurring, along with the ℓ 0 -and ℓ 1 -based TV regularizer…”

Section: ) Sparsity Optimization Modelsmentioning

confidence: 99%

Image Restoration for Remote Sensing: Overview and Toolbox

Rasti¹,

Chen²,

Dalsasso³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper is under review in GRSM. Remote sensing provides valuable information about objects or areas from a distance in either active (e.g., RADAR and LiDAR) or passive (e.g., multispectral and hyperspectral) modes. The quality of data acquired by remotely sensed imaging sensors (both active and passive) is often degraded by a variety of noise types and artifacts. Image restoration, which is a vibrant field of research in the remote sensing community, is the task of recovering the true unknown image from the degraded observed image. Each imaging sensor induces unique noise types and artifacts into the observed image. This fact has led to the expansion of restoration techniques in different paths according to each sensor type. This review paper brings together the advances of image restoration techniques with particular focuses on synthetic aperture radar and hyperspectral images as the most active sub-fields of image restoration in the remote sensing community. We, therefore, provide a comprehensive, discipline-specific starting point for researchers at different levels (i.e., students, researchers, and senior researchers) willing to investigate the vibrant topic of data restoration by supplying sufficient detail and references. Additionally, this review paper accompanies a toolbox to provide a platform to encourage interested students and researchers in the field to further explore the restoration techniques and fast-forward the community. The toolboxes are provided in https://github.com/ImageRestorationToolbox.

show abstract

“…Non-blind deblurring algorithms assume that the blur kernel is known or pre-estimated, whereas blind deblurring algorithms estimate both the blur kernel and the clear image or output the clear image directly. Early conventional deblurring models used natural image priors to design the corresponding algorithms [ 6 , 7 , 8 ]; however, when dealing with images with null-variant properties, most a priori models do not capture the complex blurring variations in real images well. To ameliorate this problem, a number of deep learning-based deblurring algorithms have been proposed, with neural networks themselves offering unique advantages that are unmatched by traditional algorithms: They generate images directly from the network without estimating fuzzy kernels, avoiding the problem of error superposition during the estimation of fuzzy kernels; There is no need to consider whether the motion blur has a spatially varying property, extending the applicability of the algorithm.…”

Section: Introductionmentioning

confidence: 99%

Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment

Zhu

Yang

et al. 2022

Sensors

View full text Add to dashboard Cite

Motion blur recovery is a common method in the field of remote sensing image processing that can effectively improve the accuracy of detection and recognition. Among the existing motion blur recovery methods, the algorithms based on deep learning do not rely on a priori knowledge and, thus, have better generalizability. However, the existing deep learning algorithms usually suffer from feature misalignment, resulting in a high probability of missing details or errors in the recovered images. This paper proposes an end-to-end generative adversarial network (SDD-GAN) for single-image motion deblurring to address this problem and to optimize the recovery of blurred remote sensing images. Firstly, this paper applies a feature alignment module (FAFM) in the generator to learn the offset between feature maps to adjust the position of each sample in the convolution kernel and to align the feature maps according to the context; secondly, a feature importance selection module is introduced in the generator to adaptively filter the feature maps in the spatial and channel domains, preserving reliable details in the feature maps and improving the performance of the algorithm. In addition, this paper constructs a self-constructed remote sensing dataset (RSDATA) based on the mechanism of image blurring caused by the high-speed orbital motion of satellites. Comparative experiments are conducted on self-built remote sensing datasets and public datasets as well as on real remote sensing blurred images taken by an in-orbit satellite (CX-6(02)). The results show that the algorithm in this paper outperforms the comparison algorithm in terms of both quantitative evaluation and visual effects.

show abstract

Texture-Aware Deblurring for Remote Sensing Images Using $ \ell _0$-Based Deblurring and $ \ell _2$-Based Fusion

Cited by 16 publications

References 35 publications

Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising

Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising

Image Restoration for Remote Sensing: Overview and Toolbox

Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment

Contact Info

Product

Resources

About