Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising

Takemoto, Shingo; Naganuma, Kazuki; Ono, Shunsuke

doi:10.1109/lgrs.2022.3192912

Cited by 14 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…I. By further generalizing the third term, RHUIDR can incorporate other regularizations proposed, e.g., in [43], [44].…”

Section: Gaussian Sparse Stripementioning

confidence: 99%

“…Therefore, we believe that incorporating spatio-spectral regularization for HS images into the unmixing formulation can improve the unmixing performance in high-noise situations where abundance maps are difficult to estimate using existing methods. Fortunately, in the context of HS image restoration, many effective HS image regularizations have been studied [38]- [44]. By adopting them as image-domain regularizations, we can robustify the unmixing process under highly-noisy scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Naganuma,

Ono

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Hyperspectral (HS) unmixing is the process of decomposing an HS image into material-specific spectra (endmembers) and their spatial distributions (abundance maps). Existing unmixing methods have two limitations with respect to noise robustness. First, if the input HS image is highly noisy, even if the balance between sparse and piecewise-smooth regularizations for abundance maps is carefully adjusted, noise may remain in the estimated abundance maps or undesirable artifacts may appear. Second, existing methods do not explicitly account for the effects of stripe noise, which is common in HS measurements, in their formulations, resulting in significant degradation of unmixing performance when such noise is present in the input HS image. To overcome these limitations, we propose a new robust hyperspectral unmixing method based on constrained convex optimization. Our method employs, in addition to the two regularizations for the abundance maps, regularizations for the HS image reconstructed by mixing the estimated abundance maps and endmembers. This strategy makes the unmixing process much more robust in highly-noisy scenarios, under the assumption that the abundance maps used to reconstruct the HS image with desirable spatio-spectral structure are also expected to have desirable properties. Furthermore, our method is designed to accommodate a wider variety of noise including stripe noise. To solve the formulated optimization problem, we develop an efficient algorithm based on a preconditioned primal-dual splitting method, which can automatically determine appropriate stepsizes based on the problem structure. Experiments on synthetic and real HS images demonstrate the advantages of our method over existing methods.

show abstract

“…I. By further generalizing the third term, RHUIDR can incorporate other regularizations proposed, e.g., in [43], [44].…”

Section: Gaussian Sparse Stripementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Naganuma,

Ono

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, the spatial-smoothness prior also leads to many total-variation-(TV)regularization-based approaches [16][17][18] that exploit the smoothness assumption of the entire HSI. Rudin [18] initially introduced the original TV-denoising method, with the aim of finding a restoration image that approximated the noisy image while minimizing the L1 norm of its spatial gradient.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Denoising Based on Principal-Third-Order-Moment Analysis

Li,

Geng,

Zhu

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Denoising serves as a critical preprocessing step for the subsequent analysis of the hyperspectral image (HSI). Due to their high computational efficiency, low-rank-based denoising methods that project the noisy HSI into a low-dimensional subspace identified by certain criteria have gained widespread use. However, methods employing second-order statistics as criteria often struggle to retain the signal of the small targets in the denoising results. Other methods utilizing high-order statistics encounter difficulties in effectively suppressing noise. To tackle these challenges, we delve into a novel criterion to determine the projection subspace, and propose an innovative low-rank-based method that successfully preserves the spectral characteristic of small targets while significantly reducing noise. The experimental results on the synthetic and real datasets demonstrate the effectiveness of the proposed method, in terms of both small-target preservation and noise reduction.

show abstract

“…As to HSI, simple band-by-band implementation of TV may destroy spectral information. Thus, some spatio-spectral extensions of TV are developed by taking account of both spatial and spectral variations, such as the Cubic TV [15], spatio-spectral TV (SSTV) [16], anisotropic SSTV [17], l 0 -l 1−2 SSTV [18], and graph SSTV [19]. The LR models exploit the spectral correlation and the nonlocal self-similarity in HSI, which are mostly realized through LR matrix recovery (LRMR) and tensor decomposition.…”

Section: Introductionmentioning

confidence: 99%

Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising

Yin,

Chen

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Despite the significant successes in hyperspectral image (HSI) denoising, pure data-driven HSI denoising networks still suffer from limited understanding of inference. Deep unfolding (DU) is a feasible way to improve the interpretability of deep network. However, the specialized spatial-spectral DU methods are seldom studied, and the simple spatial-spectral extension leads to unpleasant spectral distortion. To tackle these issues, we firstly propose a Content-Dependent 3D Convolutional Sparse Coding (CD-CSC) to jointly represent spatial-spectral feature. Specifically, the 3D filters used in CD-CSC for each HSI are unique, which are determined by linear combination of base 3D filters. Then, we develop a novel CD-CSC-inspired DU network for HSI denoising, called CD-CSCNet. Furthermore, by exploiting the lightweight of separable convolution and the adaptability of hypernetwork, we design a Separable Content-Dependent 3D Convolution (SCD-Conv) to carry out CD-CSCNet. SCD-Conv not only reduces computational complexity, but also can be viewed as the convolutional sparse coding with spatial and spectral dictionaries. Extensive experimental results on the ICVL, Zhuhai-1 OHS-3C, and GaoFen-5 datasets demonstrate that CD-CSCNet outperforms several recent pure data-driven and DU-based networks quantitatively and visually.

show abstract

Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising

Cited by 14 publications

References 34 publications

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Hyperspectral Image Denoising Based on Principal-Third-Order-Moment Analysis

Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising

Contact Info

Product

Resources

About