Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising
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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10412620/ |
| _version_ | 1797311734429515776 |
|---|---|
| author | Haitao Yin Hao Chen |
| author_facet | Haitao Yin Hao Chen |
| author_sort | Haitao Yin |
| collection | DOAJ |
| description | 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 first propose a content-dependent 3-D convolutional sparse coding (CD-CSC) to jointly represent spatial-spectral feature. Specifically, the 3-D filters used in CD-CSC for each HSI are unique, which are determined by linear combination of base 3-D 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. |
| first_indexed | 2024-03-08T02:03:56Z |
| format | Article |
| id | doaj.art-a64d117c91ac47ad85b4282a042798bc |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-08T02:03:56Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-a64d117c91ac47ad85b4282a042798bc2024-02-14T00:00:53ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01174125413810.1109/JSTARS.2024.335773210412620Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image DenoisingHaitao Yin0https://orcid.org/0000-0003-2975-2188Hao Chen1https://orcid.org/0009-0007-0600-4351College of Automation and College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, ChinaCollege of Automation and College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, ChinaDespite 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 first propose a content-dependent 3-D convolutional sparse coding (CD-CSC) to jointly represent spatial-spectral feature. Specifically, the 3-D filters used in CD-CSC for each HSI are unique, which are determined by linear combination of base 3-D 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.https://ieeexplore.ieee.org/document/10412620/Hyperspectral image denoisingdeep networkconvolutional sparse codingdeep unfolding3-D convolutionseparable convolution |
| spellingShingle | Haitao Yin Hao Chen Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Hyperspectral image denoising deep network convolutional sparse coding deep unfolding 3-D convolution separable convolution |
| title | Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising |
| title_full | Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising |
| title_fullStr | Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising |
| title_full_unstemmed | Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising |
| title_short | Deep Content-Dependent 3-D Convolutional Sparse Coding for Hyperspectral Image Denoising |
| title_sort | deep content dependent 3 d convolutional sparse coding for hyperspectral image denoising |
| topic | Hyperspectral image denoising deep network convolutional sparse coding deep unfolding 3-D convolution separable convolution |
| url | https://ieeexplore.ieee.org/document/10412620/ |
| work_keys_str_mv | AT haitaoyin deepcontentdependent3dconvolutionalsparsecodingforhyperspectralimagedenoising AT haochen deepcontentdependent3dconvolutionalsparsecodingforhyperspectralimagedenoising |