Hyperspectral image restoration by Hybrid Spatio-Spectral Total Variation

Takeyama, Saori; Ono, Shunsuke; Kumazawa, Itsuo

doi:10.1109/icassp.2017.7953025

Cited by 21 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model employs spike-slob sparse prior to recognize sparse coefficients of the real data term and outlier noise. An algorithm for jointly denoising hyperspectral images corrupted by mixed Gaussian plus impulse noise has ben proposed in [16]- [18]. The proposed algorithm avails the inherent spatial and spectral correlation of such images.…”

Section: Related Workmentioning

confidence: 99%

Image mixed gaussian and impulse noise elimination based on sparse representation model

Hussein

Hussain²,

Reja

2021

IJEECS

View full text Add to dashboard Cite

<p>A modified mixed Gaussian plus impulse image denoising algorithm based on weighted encoding with image sparsity and nonlocal self-similarity priors regularization is proposed in this paper. The encoding weights and the priors imposed on the images are incorporated into a variational framework to treat more complex mixed noise distribution. Such noise is characterized by heavy tails caused by impulse noise which needs to be eliminated through proper weighting of encoding residual. The outliers caused by the impulse noise has a significant effect on the encoding weights. Hence a more accurate residual encoding error initialization plays the important role in overall denoising performance, especially at high impulse noise rates. In this paper, outliers free initialization image, and an easier to implement a parameter-free procedure for updating encoding weights have been proposed. Experimental results demonstrate the capability of the proposed strategy to recover images highly corrupted by mixed Gaussian plus impulse noise as compared with the state of art denoising algorithm. The achieved results motivate us to implement the proposed algorithm in practice.</p>

show abstract

Section: Related Workmentioning

confidence: 99%

Image mixed gaussian and impulse noise elimination based on sparse representation model

Hussein

Hussain²,

Reja

2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…Furthermore, based on the property of piecewise smoothness, various total variation (TV)-based algorithms [28][29][30][31] have been designed for HSI denoising. As reported in reference [32], these methods always attempt to preserve the structural information, such as edges or textures, better when smoothing the noise in homogeneous areas.…”

Section: Introductionmentioning

confidence: 99%

Total Variation Regularized Low-Rank Model With Directional Information for Hyperspectral Image Restoration

et al. 2021

View full text Add to dashboard Cite

Hyperspectral images (HSIs) are unavoidably polluted by various kinds of noise, which decrease the potential of subsequent processes in HSIs applications. Due to the diversity and complexity of HSIs mixed noise, including impulse noise, Gaussian noise, stripe noise and deadlines, traditional restoration technology cannot be used directly. In this paper, a novel HSIs restoration approach is proposed that integrates low-rank (LR) prior and spatial-spectral total variation with directional information. Specifically, by analyzing the characteristic of spatial-dependent edge and texture directional structure, a spatial-spectral directional total variation (SSDTV) regularization is defined. Then, considering the HSIs as a cube data, the proposed method utilizes SSDTV regularization to characterize spatial-spectral smoothness, as well as LR regularization to constrain spectral consistency. Finally, an extended alternating direction method of multipliers algorithm is designed to achieve simple and fast implementation, in which the complex optimization problem is separated into several easier subproblems. Both simulated and real-world HSIs experiments indicated that the proposed method is effective and numerically feasible for HSIs Restoration.

show abstract

“…Unlike STV and ASTV, noise tends to remain in the restoration results of LRMR and SSTV because of the weak influence of the spatial properties. Other methods that exploit the low-rankness, such as LRTV [8] and LRTDTV [30], attempt to improve the performance of STV, SSTV, and its variants [28] by newly introducing regularization. These methods offer excellent performance, especially when a model matches a real degradation process, and offer an advantage in that learning with a large dataset is not necessary.…”

Section: Introductionmentioning

confidence: 99%

Zero-Shot Hyperspectral Image Denoising With Separable Image Prior

Imamura

Itasaka

Okuda

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Supervised learning with a convolutional neural network is recognized as a powerful means of image restoration. However, most such methods have been designed for application to grayscale and/or color images; therefore, they have limited success when applied to hyperspectral image restoration. This is partially owing to large datasets being difficult to collect, and also the heavy computational load associated with the restoration of an image with many spectral bands. To address this difficulty, we propose a novel self-supervised learning strategy for application to hyperspectral image restoration. Our method automatically creates a training dataset from a single degraded image and trains a denoising network without any clear images. Another notable feature of our method is the use of a separable convolutional layer.We undertake experiments to prove that the use of a separable network allows us to acquire the prior of a hyperspectral image and to realize efficient restoration. We demonstrate the validity of our method through extensive experiments and show that our method has better characteristics than those that are currently regarded as state-of-the-art.

show abstract

Hyperspectral image restoration by Hybrid Spatio-Spectral Total Variation

Cited by 21 publications

References 27 publications

Image mixed gaussian and impulse noise elimination based on sparse representation model

Image mixed gaussian and impulse noise elimination based on sparse representation model

Total Variation Regularized Low-Rank Model With Directional Information for Hyperspectral Image Restoration

Zero-Shot Hyperspectral Image Denoising With Separable Image Prior

Contact Info

Product

Resources

About