Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914897099489280 |
|---|---|
| author | Liang, Hao Chengjie Li, Kun Tian, Xin |
| author_facet | Liang, Hao Chengjie Li, Kun Tian, Xin |
| contents | Hyperspectral image (HSI) denoising is an essential procedure for HSI applications. Unfortunately, the existing Transformer-based methods mainly focus on non-local modeling, neglecting the importance of locality in image denoising. Moreover, deep learning methods employ complex spectral learning mechanisms, thus introducing large computation costs.
To address these problems, we propose a hybrid spatial-spectral denoising network (HSSD), in which we design a novel hybrid dual-path network inspired by CNN and Transformer characteristics, leading to capturing both local and non-local spatial details while suppressing noise efficiently. Furthermore, to reduce computational complexity, we adopt a simple but effective decoupling strategy that disentangles the learning of space and spectral channels, where multilayer perception with few parameters is utilized to learn the global correlations among spectra. The synthetic and real experiments demonstrate that our proposed method outperforms state-of-the-art methods on spatial and spectral reconstruction. The code and details are available on https://github.com/HLImg/HSSD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08782 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising Liang, Hao Chengjie Li, Kun Tian, Xin Image and Video Processing Computer Vision and Pattern Recognition Hyperspectral image (HSI) denoising is an essential procedure for HSI applications. Unfortunately, the existing Transformer-based methods mainly focus on non-local modeling, neglecting the importance of locality in image denoising. Moreover, deep learning methods employ complex spectral learning mechanisms, thus introducing large computation costs. To address these problems, we propose a hybrid spatial-spectral denoising network (HSSD), in which we design a novel hybrid dual-path network inspired by CNN and Transformer characteristics, leading to capturing both local and non-local spatial details while suppressing noise efficiently. Furthermore, to reduce computational complexity, we adopt a simple but effective decoupling strategy that disentangles the learning of space and spectral channels, where multilayer perception with few parameters is utilized to learn the global correlations among spectra. The synthetic and real experiments demonstrate that our proposed method outperforms state-of-the-art methods on spatial and spectral reconstruction. The code and details are available on https://github.com/HLImg/HSSD. |
| title | Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.08782 |